To see the other types of publications on this topic, follow the link: Real-Time Pose Detection.
Journal articles on the topic 'Real-Time Pose Detection'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Real-Time Pose Detection.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
K, Athira. "Real-Time feedback system for Accurate Yoga Pose Detection." International Journal of Research Publication and Reviews 6, no. 5 (2025): 11297–303. https://doi.org/10.55248/gengpi.6.0525.1898.
Full text
2
Meng, Zhichao, Xiaoqiang Du, Ranjan Sapkota, Zenghong Ma, and Hongchao Cheng. "YOLOv10-pose and YOLOv9-pose: Real-time strawberry stalk pose detection models." Computers in Industry 165 (February 2025): 104231. https://doi.org/10.1016/j.compind.2024.104231.
Full text
3
Di Natali, Christian, Marco Beccani, and Pietro Valdastri. "Real-Time Pose Detection for Magnetic Medical Devices." IEEE Transactions on Magnetics 49, no. 7 (2013): 3524–27. http://dx.doi.org/10.1109/tmag.2013.2240899.
Full text
4
Nagargoje, Shrinivas, Adesh Shinde, Pranav Tapadiya, Om Shinde, and Prof Anita Devkar. "Yoga Pose Detection." International Journal for Research in Applied Science and Engineering Technology 11, no. 5 (2023): 2053–60. http://dx.doi.org/10.22214/ijraset.2023.51821.
Full textAbstract:
Abstract: This paper describes a real-time yoga pose detection system that can accurately classify and detect yoga poses in images using Convolutional Neural Networks (CNNs) and OpenPose. By using OpenPose, the system generates a 3D joint map of the person's body, which is then used as input for linear regression to detect the individual yoga pose. The system is suitable for real-time applications, and is expected to be used in fitness centers, yoga studios, and even for personal use. Additionally, the system can also be used to track the progress of yoga practitioners, allowing them to analyze their performance and improve their practice. Furthermore, the proposed system is expected to benefit the yoga industry by providing a low- cost, efficient, and accurate means to detect poses.
5
Sidana, Khushi. "REAL TIME YOGA POSE DETECTION USING DEEPLEARNING: A REVIEW." International Journal of Engineering Applied Sciences and Technology 7, no. 7 (2022): 61–65. http://dx.doi.org/10.33564/ijeast.2022.v07i07.011.
Full textAbstract:
With the increase in the number of yoga practitioners every year, the risk of injuries as a result of incorrect yoga postures has also increased. A selftraining model that can evaluate the posture of individuals is the optimal solution for this issue. This objective can be attained with the aid of computer vision and deep learning. A model that can detect theyoga pose performed by an individual, evaluate it in comparison to the pose performed by an expert, and provide the individual with instructive feedback would be an effective solution to this problem. Recently, numerous researchers have conducted experiments on the detection and performance of yoga poses in real time. This paper discusses the methods undertaken in brief and compares the tools and algorithms they used for conducting pose estimation, pose detection as well as pose assessment. Itdiscusses the accuracy, precision, and similarity of pose classification obtained by the researchers and the future scope of the research.
6
Nenchoo and Tantrairatn. "Real-Time 3D UAV Pose Estimation by Visualization." Proceedings 39, no. 1 (2020): 18. http://dx.doi.org/10.3390/proceedings2019039018.
Full textAbstract:
This paper presents an estimation of 3D UAV position in real-time condition by using Intel RealSense Depth camera D435i with visual object detection technique as a local positioning system for indoor environment. Nowadays, global positioning system or GPS is able to specify UAV position for outdoor environment. However, for indoor environment GPS hasn’t a capability to determine UAV position. Therefore, Depth stereo camera D435i is proposed to observe on ground to specify UAV position for indoor environment instead of GPS. Using deep learning for object detection to identify target object with depth camera to specifies 2D position of target object. In addition, depth position is estimated by stereo camera and target size. For experiment, Parrot Bebop2 as a target object is detected by using YOLOv3 as a real-time object detection system. However, trained Fully Convolutional Neural Networks (FCNNs) model is considerably significant for object detection, thus the model has been trained for bebop2 only. To conclude, this proposed system is able to specifies 3D position of bebop2 for indoor environment. For future work, this research will be developed and apply for visualized navigation control of drone swarm.
7
Bhargavi, Mrs Jangam, Chitikala Sairam, and Donga Hemanth. "Real time interface for deaf-hearing communication." International Scientific Journal of Engineering and Management 04, no. 03 (2025): 1–7. https://doi.org/10.55041/isjem02356.
Full textAbstract:
Bridging the communication gap between the deaf and hearing communities using AI is achieved by integrating two key modules: Speech-to-Sign Language Translation and Sign Gesture Detection in Real Time. The first module translates English spoken language into American Sign Language (ASL) animations. It consists of three sub-modules: speech-to-text conversion using the speech recognition module in Python, English text to ASL gloss translation using an NLP model, and ASL gloss to animated video generation, where DWpose Pose Estimation, and an avatar is used for visual representation. The second module focuses on real-time sign gesture detection, where a dataset is created from the WLASL and MS-ASL datasets. Hand gestures are labeled using Labeling, and a YOLO-based model is trained for hand pose detection to enable real-time recognition. The system aims to enhance accessibility and interaction between deaf and hearing users through an efficient, automated translation and recognition pipeline. Keywords: Speech-to-sign translation, real-time sign language recognition, ASL gloss, YOLO hand pose detection, AI for accessibility, deep learning for sign language, gesture recognition, DWpose Pose Estimation, NLP, dataset labeling, real-time gesture recognition.
8
Liu, Yonghui, Weimin Zhang, Fangxing Li, Zhengqing Zuo, and Qiang Huang. "Real-Time Lidar Odometry and Mapping with Loop Closure." Sensors 22, no. 12 (2022): 4373. http://dx.doi.org/10.3390/s22124373.
Full textAbstract:
Real-time performance and global consistency are extremely important in Simultaneous Localization and Mapping (SLAM) problems. Classic lidar-based SLAM systems often consist of front-end odometry and back-end pose optimization. However, due to expensive computation, it is often difficult to achieve loop-closure detection without compromising the real-time performance of the odometry. We propose a SLAM system where scan-to-submap-based local lidar odometry and global pose optimization based on submap construction as well as loop-closure detection are designed as separated from each other. In our work, extracted edge and surface feature points are inserted into two consecutive feature submaps and added to the pose graph prepared for loop-closure detection and global pose optimization. In addition, a submap is added to the pose graph for global data association when it is marked as in a finished state. In particular, a method to filter out false loops is proposed to accelerate the construction of constraints in the pose graph. The proposed method is evaluated on public datasets and achieves competitive performance with pose estimation frequency over 15 Hz in local lidar odometry and low drift in global consistency.
9
Vatsal, Prince. "Real-Time Human Pose Estimation Using Machine Learning." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 05 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem34377.
Full textAbstract:
Human pose estimation is a pivotal domain within computer vision, underpinning applications from motion capture in cinematic production to sophisticated user interfaces in desktop devices. This research delineates the implementation of real-time human pose estimation within web browsers utilizing TensorFlow.js and the PoseNet model. PoseNet, an advanced machine learning model optimized for browser-based execution, facilitates precise pose detection sans specialized hardware. The primary aim of this study is to integrate PoseNet with TensorFlow.js, achieving efficient real-time pose estimation directly in the browser by leveraging JavaScript, thereby ensuring seamless user interaction and broad accessibility. A modular system architecture is designed, focusing on optimization strategies such as model quantization, asynchronous processing, and on-device computation to enhance performance and privacy preservation. In conclusion, this research establishes a robust framework for deploying PoseNet in web environments, underscoring its potential to revolutionize human-computer interaction within browser-based applications. Our findings contribute significantly to the field of computer vision and machine learning, offering insights into the practical deployment of pose estimation models on widely accessible platforms. Keywords — ReaReal-time Pose Estimation, TensorFlow.js, PoseNet, Machine Learning, Computer Vision, Browser-based Pose Detection, Human-Computer Interaction, Multi-person Tracking, On-device Computation, Asynchronous Processing, Cross-browser Compatibility, Performance Optimization, Privacy-preserving AI, Web-based Machine Learning, Motion Capture, Fitness Tracking, Interactive , Virtual Reality Interfaces, Deep LearningLearning
10
Mulla, A. S. "Real-Time Cyber Security Protection Tool." International Journal for Research in Applied Science and Engineering Technology 13, no. 1 (2025): 183–86. https://doi.org/10.22214/ijraset.2025.65807.
Full textAbstract:
This report aims to examine the evolving cybersecurity threats, including DeepFakes, phishing, social engineering, and malware, and analyze detection mechanisms to counter these threats. DeepFakes, generated using advanced AI techniques, pose risks such as identity theft and disinformation, with detection models like CNNs and RNNs showing promise, albeit with reduced effectiveness against high-quality manipulations. Tools like Face Forensics++ are instrumental for training such models. Phishing, which employs deceptive techniques to steal sensitive information, is addressed through URL-based detection systems and datasets such as Phish-Tank. Social engineering, leveraging tactics like pretexting and baiting, highlights the importance of NLP models for detecting manipulation in communications. Malware, encompassing threats like ransomware and spyware, continues to challenge cybersecurity efforts, with machine learning and deep learning approaches proving effective for detection. Tools like Virus Total and Cuckoo Sandbox enhance detection through multi-engine scanning and dynamic analysis. While detection technologies show significant potential, challenges such as real-time threat identification and user awareness underscore the need for integrated, adaptive cybersecurity solutions
11
Lu, Tianyi, Ke Cheng, Xuecheng Hua, and Suning Qin. "KSL-POSE: A Real-Time 2D Human Pose Estimation Method Based on Modified YOLOv8-Pose Framework." Sensors 24, no. 19 (2024): 6249. http://dx.doi.org/10.3390/s24196249.
Full textAbstract:
Two-dimensional human pose estimation aims to equip computers with the ability to accurately recognize human keypoints and comprehend their spatial contexts within media content. However, the accuracy of real-time human pose estimation diminishes when processing images with occluded body parts or overlapped individuals. To address these issues, we propose a method based on the YOLO framework. We integrate the convolutional concepts of Kolmogorov–Arnold Networks (KANs) through introducing non-linear activation functions to enhance the feature extraction capabilities of the convolutional kernels. Moreover, to improve the detection of small target keypoints, we integrate the cross-stage partial (CSP) approach and utilize the small object enhance pyramid (SOEP) module for feature integration. We also innovatively incorporate a layered shared convolution with batch normalization detection head (LSCB), consisting of multiple shared convolutional layers and batch normalization layers, to enable cross-stage feature fusion and address the low utilization of model parameters. Given the structure and purpose of the proposed model, we name it KSL-POSE. Compared to the baseline model YOLOv8l-POSE, KSL-POSE achieves significant improvements, increasing the average detection accuracy by 1.5% on the public MS COCO 2017 data set. Furthermore, the model also demonstrates competitive performance on the CrowdPOSE data set, thus validating its generalization ability.
12
Tu, Haiyan, Zhengkun Qiu, Kang Yang, Xiaoyue Tan, and Xiujuan Zheng. "HP-YOLO: A Lightweight Real-Time Human Pose Estimation Method." Applied Sciences 15, no. 6 (2025): 3025. https://doi.org/10.3390/app15063025.
Full textAbstract:
Human Pose Estimation (HPE) plays a critical role in medical applications, particularly within nursing robotics for patient monitoring. Despite its importance, HPE faces several challenges, including high rates of false positives and negatives, stringent real-time requirements, and limited computational resources, especially in complex backgrounds. In response, we introduce the HP-YOLO model, developed using the YOLOv8 framework, to effectively address these issues. We designed an Enhanced Large Separated Kernel Attention (ELSKA) mechanism and integrated it into the backbone network, thereby improving the model’s effective receptive field and feature separation capabilities, which enhances keypoint detection accuracy in challenging environments. Additionally, the Reparameterized Network with Cross-Stage Partial Connections and Efficient Layer Aggregation Network (RepNCSPELAN4) module was incorporated into the detection head, boosting accuracy in detecting small-sized targets through multi-scale convolution and reparameterization techniques while accelerating inference speed. On the COCO dataset, our HP-YOLO model outperformed existing lightweight methods by increasing average precision (AP) by 4.9%, while using 18% fewer parameters and achieving 1.4× higher inference speed. Our method significantly enhances the real-time performance and efficiency of human pose estimation while maintaining high accuracy, offering an optimal solution for applications in complex environments.
13
Tîrziu, Eugenia, Ana-Mihaela Vasilevschi, Adriana Alexandru, and Eleonora Tudora. "Enhanced Fall Detection Using YOLOv7-W6-Pose for Real-Time Elderly Monitoring." Future Internet 16, no. 12 (2024): 472. https://doi.org/10.3390/fi16120472.
Full textAbstract:
This study aims to enhance elderly fall detection systems by using the YOLO (You Only Look Once) object detection algorithm with pose estimation, improving both accuracy and efficiency. Utilizing YOLOv7-W6-Pose’s robust real-time object detection and pose estimation capabilities, the proposed system can effectively identify falls in video feeds by using a webcam and process them in real-time on a high-performance computer equipped with a GPU to accelerate object detection and pose estimation algorithms. YOLO’s single-stage detection mechanism enables quick processing and analysis of video frames, while pose estimation refines this process by analyzing body positions and movements to accurately distinguish falls from other activities. Initial validation was conducted using several free videos sourced online, depicting various types of falls. To ensure real-time applicability, additional tests were conducted with videos recorded live using a webcam, simulating dynamic and unpredictable conditions. The experimental results demonstrate significant advancements in detection accuracy and robustness compared to traditional methods. Furthermore, the approach ensures data privacy by processing only skeletal points derived from pose estimation, with no personal data stored. This approach, integrated into the NeuroPredict platform developed by our team, advances fall detection technology, supporting better care and safety for older adults.
14
Pauwels, Karl, Leonardo Rubio, and Eduardo Ros. "Real-Time Pose Detection and Tracking of Hundreds of Objects." IEEE Transactions on Circuits and Systems for Video Technology 26, no. 12 (2016): 2200–2214. http://dx.doi.org/10.1109/tcsvt.2015.2430652.
Full text
15
Pingale, Sahil. "Yoga Pose Detection and Feedback System." International Journal for Research in Applied Science and Engineering Technology 13, no. 5 (2025): 3668–77. https://doi.org/10.22214/ijraset.2025.70791.
Full textAbstract:
Abstract: Human pose estimation plays a vital role in various domains, including fitness tracking, physiotherapy, sports performance analysis, and human-computer interaction. Accurate posture detection is essential to prevent injuries, improve physical activity performance, and aid rehabilitation processes. This research presents a real-time human pose detection and feedback system leveraging the MoveNet deep learning model and TensorFlow. The system captures live video streams using OpenCV, processes the frames with MoveNet to extract key joint positions, and applies an angle calculation module to evaluate movement accuracy. To enhance accessibility and usability, the system integrates a graphical user interface (GUI) built with Tkinter and a text-to-speech feedback mechanism to provide real-time guidance. The effectiveness of the system is validated through comparative analysis with standard pose models, ensuring that users receive real-time feedback on their posture deviations. The experimental results demonstrate high detection accuracy, rapid processing speeds, and enhanced user engagement, making it a viable solution for automated fitness coaching, physiotherapy monitoring, and interactive learning applications. Additionally, the system reduces the reliance on human instructors by offering automated posture correction, thereby democratizing access to professional-level movement assessment
16
Li, Xiaowu, Kun Sun, Hongbo Fan, and Zihan He. "Real-Time Cattle Pose Estimation Based on Improved RTMPose." Agriculture 13, no. 10 (2023): 1938. http://dx.doi.org/10.3390/agriculture13101938.
Full textAbstract:
Accurate cattle pose estimation is essential for Precision Livestock Farming (PLF). Computer vision-based, non-contact cattle pose estimation technology can be applied for behaviour recognition and lameness detection. Existing methods still face challenges in achieving fast cattle pose estimation in complex scenarios. In this work, we introduce the FasterNest Block and Depth Block to enhance the performance of cattle pose estimation based on the RTMPose model. First, the accuracy of cattle pose estimation relies on the capture of high-level image features. The FasterNest Block, with its three-branch structure, effectively utilizes high-level feature map information, significantly improving accuracy without a significant decrease in inference speed. Second, large kernel convolutions can increase the computation cost of the model. Therefore, the Depth Block adopts a method based on depthwise separable convolutions to replace large kernel convolutions. This addresses the insensitivity to semantic information while reducing the model’s parameter. Additionally, the SimAM module enhances the model’s spatial learning capabilities without introducing extra parameters. We conducted tests on various datasets, including our collected complex scene dataset (cattle dataset) and the AP-10K public dataset. The results demonstrate that our model achieves the best average accuracy with the lowest model parameters and computational requirements, achieving 82.9% on the cattle test set and 72.0% on the AP-10K test set. Furthermore, in conjunction with the object detection model RTMDet-m, our model reaches a remarkable inference speed of 39FPS on an NVIDIA GTX 2080Ti GPU using the PyTorch framework, making it the fastest among all models. This work provides adequate technical support for fast and accurate cattle pose estimation in complex farm environments.
17
G, Manisha, Meenakshi N.A., Srinithi S, Rajalakshmi Murugesan, and Sheikh Mastan S.A.R. "VR–BASED YOGA POSTURE DETECTION, CLASSIFICATION AND CORRECTION." ICTACT Journal on Data Science and Machine Learning 6, no. 3 (2025): 829–34. https://doi.org/10.21917/ijdsml.2025.0166.
Full textAbstract:
Yoga promotes physical and mental health but practicing correct posture alignment without expert help isn't easy. To solve these problems, we propose a VR-based yoga posture detection, classification, and correction system in this research. Real-time images of yoga poses were captured using an ESP32-CAM interfaced with Arduino and processed with Python. Mediapipe and OpenCV frameworks are responsible for pose detection and classification. At the same time, angle-based calculations help to detect whether the user has achieved Bridge Pose, Mountain Pose, Downward Dog pose, and Warrior II pose. Real-time voice feedback helps users fine-tune their alignment. This system has combined Blynk software with Unity to build an immersive virtual reality experience where a headset shows off pose animations. Combining AI and VR ensures the solution connects practitioners to expert instruction and correct posture in real time, ultimately enhancing the benefits of yoga as a practice.
18
Borkar, Yasar, Reeve Mascarenhas, Shubham Tambadkar, and Jayanand P. Gawande. "Comparison of Real-Time Face Detection and Recognition Algorithms." ITM Web of Conferences 44 (2022): 03046. http://dx.doi.org/10.1051/itmconf/20224403046.
Full textAbstract:
With the phenomenal growth of video and image databases, there is a tremendous need for intelligent systems to automatically understand and examine information, as doing so manually is becoming increasingly difficult. The face is important in social interactions because it conveys information. Detecting a person's identity and feelings Humans do not have a great deal of ability to identify. Machines have different faces. As a result, an automatic face detection system is essential.in face recognition, facial expression recognition, head-pose estimation, and human–computer interaction, and so on Face detection is a computer technology that determines the location and size of a person's face. It also creates a digital image of a human face. Face detection has been a standout topic in the science field This paper provides an in-depth examination of the various techniques investigated for face detection in digital images. Various face challenges and applications. This paper also discusses detection. Detection features are also provided. In addition, we hold special discussions on the practical aspects of developing a robust face detection system, and finally. This paper concludes with several promising research directions for the future.
19
Mahajan, Priyanshu, Shambhavi Gupta, and Divya Kheraj Bhanushali. "Body Pose Estimation using Deep Learning." International Journal for Research in Applied Science and Engineering Technology 11, no. 3 (2023): 1419–24. http://dx.doi.org/10.22214/ijraset.2023.49688.
Full textAbstract:
Abstract: Healthcare, sports analysis, gaming, and entertain- ment are just some of the many fields that could benefit from solving the challenging issue of real-time human pose detection and recognition in computer vision. Capturing human motion, analysing physical exercise, and giving feedback on performance can all benefit from reliable detection and recognition of body poses. The recent progress in deep learning has made it possible to create real-time systems that can accurately and quickly recognise and identify human poses.
20
Di Natali, Christian, Marco Beccani, Keith L. Obstein, and Pietro Valdastri. "Sa1622 Wireless Real-Time Pose Detection for Magnetic Manipulated Endoscopic Capsules." Gastrointestinal Endoscopy 77, no. 5 (2013): AB270—AB271. http://dx.doi.org/10.1016/j.gie.2013.03.673.
Full text
21
do Monte Lima, João Paulo Silva, Francisco Paulo Magalhães Simões, Hideaki Uchiyama, Veronica Teichrieb, and Eric Marchand. "Depth-assisted rectification for real-time object detection and pose estimation." Machine Vision and Applications 27, no. 2 (2015): 193–219. http://dx.doi.org/10.1007/s00138-015-0740-8.
Full text
22
Aryawan, Putu Oki Wiradita, I. Dewa Gede Wicaksana Prabaswara, Altaf Husain, et al. "Real-time estrus detection in cattle using deep learning-based pose estimation." BIO Web of Conferences 123 (2024): 04009. http://dx.doi.org/10.1051/bioconf/202412304009.
Full textAbstract:
Accurate estrus detection is of paramount importance for optimizing the reproductive efficiency of livestock. Traditional methods are often labor-intensive and subjective. The cow estrus period, which only lasts 12-24 hours in a cycle that repeats every 18-24 days, causes the opportunity to mate or perform artificial insemination to be missed. This study proposes a novel approach that utilizes pose estimation with a deep learning model for real-time estrus detection in female cows. We collected a dataset of annotated images of cows at different estrus stages and developed a deep learning model based on the EfficientPose architecture. The cow estrus parameter analyzed was locomotion activity, which was categorized into lying down and standing classes with an integrated system and LCD-displayed detection results. The Jetson Nano and YOLOv5 algorithms processed the input parameter data with a mean average precision (mAP) of 0.8 and a final loss prediction value of 0.01. If the female cow is classified as active (number of lying down classes < 57,600 classes/h), then the cow is considered to be in the estrus period. This system provides reliable and non-invasive estrus detection, enabling timely intervention for improved reproductive management in cattle farming.
23
Chen, Haijian, Xinyun Jiang, and Yonghui Dai. "Shift Pose: A Lightweight Transformer-like Neural Network for Human Pose Estimation." Sensors 22, no. 19 (2022): 7264. http://dx.doi.org/10.3390/s22197264.
Full textAbstract:
High-performing, real-time pose detection and tracking in real-time will enable computers to develop a finer-grained and more natural understanding of human behavior. However, the implementation of real-time human pose estimation remains a challenge. On the one hand, the performance of semantic keypoint tracking in live video footage requires high computational resources and large parameters, which limiting the accuracy of pose estimation. On the other hand, some transformer-based models were proposed recently with outstanding performance and much fewer parameters and FLOPs. However, the self-attention module in the transformer is not computationally friendly, which makes it difficult to apply these excellent models to real-time jobs. To overcome the above problems, we propose a transformer-like model, named ShiftPose, which is regression-based approach. The ShiftPose does not contain any self-attention module. Instead, we replace the self-attention module with a non-parameter operation called the shift operator. Meanwhile, we adapt the bridge–branch connection, instead of a fully-branched connection, such as HRNet, as our multi-resolution integration scheme. Specifically, the bottom half of our model adds the previous output, as well as the output from the top half of our model, corresponding to its resolution. Finally, the simple, yet promising, disentangled representation (SimDR) was used in our study to make the training process more stable. The experimental results on the MPII datasets were 86.4 PCKH, 29.1PCKH@0.1. On the COCO dataset, the results were 72.2 mAP and 91.5 AP50, 255 fps on GPU, with 10.2M parameters, and 1.6 GFLOPs. In addition, we tested our model for single-stage 3D human pose estimation and draw several useful and exploratory conclusions. The above results show good performance, and this paper provides a new method for high-performance, real-time attitude detection and tracking.
24
Lee, Jieun, Tae-yong Kim, Seunghyo Beak, Yeeun Moon, and Jongpil Jeong. "Real-Time Pose Estimation Based on ResNet-50 for Rapid Safety Prevention and Accident Detection for Field Workers." Electronics 12, no. 16 (2023): 3513. http://dx.doi.org/10.3390/electronics12163513.
Full textAbstract:
The present study proposes a Real-Time Pose Estimation technique using OpenPose based on ResNet-50 that enables rapid safety prevention and accident detection among field workers. Field workers perform tasks in high-risk environments, and accurate Pose Estimation is a crucial aspect of ensuring worker safety. However, it is difficult for Real-Time Pose Estimation to be conducted in such a way as to simultaneously meet Real-Time processing requirements and accuracy in complex environments. To address these issues, the current study uses the OpenPose algorithm based on ResNet-50, which is a neural network architecture that performs well in both image classification and feature extraction tasks, thus providing high accuracy and efficiency. OpenPose is an algorithm specialized for multi-human Pose Estimation that can be used to estimate the body structure and joint positions of a large number of individuals in real time. Here, we train ResNet-50-based OpenPose for Real-Time Pose Estimation and evaluate it on various datasets, including actions performed by real field workers. The experimental results show that the proposed algorithm achieves high accuracy in the Real-Time Pose Estimation of field workers. It also provides stable results while maintaining a fast image processing speed, thus confirming its applicability in real field environments.
25
Bandi, Chaitanya, and Ulrike Thomas. "Action Recognition via Multi-View Perception Feature Tracking for Human–Robot Interaction." Robotics 14, no. 4 (2025): 53. https://doi.org/10.3390/robotics14040053.
Full textAbstract:
Human–Robot Interaction (HRI) depends on robust perception systems that enable intuitive and seamless interaction between humans and robots. This work introduces a multi-view perception framework designed for HRI, incorporating object detection and tracking, human body and hand pose estimation, unified hand–object pose estimation, and action recognition. We use the state-of-the-art object detection architecture to understand the scene for object detection and segmentation, ensuring high accuracy and real-time performance. In interaction environments, 3D whole-body pose estimation is necessary, and we integrate an existing work with high inference speed. We propose a novel architecture for 3D unified hand–object pose estimation and tracking, capturing real-time spatial relationships between hands and objects. Furthermore, we incorporate action recognition by leveraging whole-body pose, unified hand–object pose estimation, and object tracking to determine the handover interaction state. The proposed architecture is evaluated on large-scale, open-source datasets, demonstrating competitive accuracy and faster inference times, making it well-suited for real-time HRI applications.
26
Mane, Deepak, Gopal Upadhye, Vinit Gite, Girish Sarwade, Gourav Kamble, and Aditya Pawar. "Smart Yoga Assistant: SVM-based Real-time Pose Detection and Correction System." International Journal on Recent and Innovation Trends in Computing and Communication 11, no. 7s (2023): 251–62. http://dx.doi.org/10.17762/ijritcc.v11i7s.6997.
Full textAbstract:
SVM-based Real-time Pose Detection and Correction System refer to a computer system that uses machine learning techniques to detect and correct a person's yoga pose in real-time. This system can act as a virtual yoga assistant, helping people improve their yoga practice by providing immediate feedback on their form and helping to prevent injury. This paper presents a yoga tracker and correction system that uses computer vision and machine learning algorithms to track and correct yoga poses. The system comprises a camera and a computer vision module that captures images of the yoga practitioner and identifies the poses being performed. The machine learning module analyzes the images to provide feedback on the quality of the poses and recommends corrections to improve form and prevent injuries. This paper proposed a customized support vector machine (SVM) based real-time pose detection and correction system that suggests yoga practices based on specific health conditions or diseases. Paper aims to provide a reliable and accessible resource for individuals seeking to use yoga as a complementary approach to managing their health conditions. The system also includes a practitioner’s interface that enables practitioners to receive personalized recommendations for their yoga practice. The system is developed using Python and several open-source libraries, and was tested on a dataset of yoga poses. The hyper parameter gamma tuned to optimize the classification accuracy on our dataset produced 87% which is better than other approaches. The experiment results demonstrate the effectiveness of the system in tracking and correcting yoga poses, and its potential to enhance the quality of yoga practice.
27
Zamindar, Tayyaba, Shradhatai Gangawane, Shital Kalane, and Yogita Kalane. "Real-Time Face Recognition and Detection Using Python." International Journal for Research in Applied Science and Engineering Technology 10, no. 5 (2022): 2745–47. http://dx.doi.org/10.22214/ijraset.2022.42939.
Full textAbstract:
Abstract: While humans can recognize faces without much effort, facial recognition is a challenging pattern recognition problem in computing. Facial recognition systems attempt to identify a human face, which is three-dimensional and changes in appearance with lighting and facial expression, based on its two-dimensional image. To accomplish this computational task, facial recognition systems perform four steps. First face detection is used to segment the face from the image background. In the second step the segmented face image is aligned to account for face pose, image size and photographic properties, such as illumination and grayscale. The purpose of the alignment process is to enable the accurate localization of facial features in the third step, the facial nature extraction. Features such as eyes, nose and mouth are pinpointed and measured in the image to represent the face. The so established feature vector of the face is then, in the fourth step, matched against a database of faces. Keywords: face, detection, recognition, system, OpenCV
28
Liu, Leyuan, Wenting Gui, Li Zhang, and Jingying Chen. "Real-time pose invariant spontaneous smile detection using conditional random regression forests." Optik 182 (April 2019): 647–57. http://dx.doi.org/10.1016/j.ijleo.2019.01.020.
Full text
29
Bhamre, Samruddhi. "A Review of Ai-Powered Human Posture Detection for Multi-Context Recognition." International Scientific Journal of Engineering and Management 04, no. 04 (2025): 1–7. https://doi.org/10.55041/isjem03226.
Full textAbstract:
ABSTRACT - This project introduces a real-time abnormal activity detection system that leverages pose estimation and K-Nearest Neighbors (KNN) classification to enhance security monitoring and ensure public safety. Conventional surveillance systems often rely heavily on manual monitoring, leading to delayed responses and potential oversight, particularly in crowded and dynamic environments. Our approach uses pose estimation techniques to capture human skeletal structures and extract key joint coordinates, enabling the accurate analysis of movement patterns. These pose-based features are normalized and classified using the KNN algorithm to distinguish between normal and abnormal activities. An intelligent alert system is integrated to notify relevant authorities immediately upon detecting suspicious behavior, ensuring timely intervention. Additionally, a user-friendly interface provides real-time visualization, system logs, and analytical insights for enhanced situational awareness. This solution not only improves the accuracy and efficiency of behavior recognition but also automates security in diverse environments such as public spaces, transportation hubs, and restricted areas, addressing challenges related to scalability, response time, and minimizing human effort. Key Words: Abnormal Activity Detection, Feature Extraction, KNN, Normalization, Pose Estimation, Skeleton Tracking
30
Nethravathi, P. S., and S. Aithal P. "Real Time Body Orientation Recognition for Customer Pose Orientation." International Journal of Management, Technology, and Social Sciences (IJMTS) 7, no. 1 (2022): 390–99. https://doi.org/10.5281/zenodo.6556192.
Full textAbstract:
<strong>Background/Purpose</strong><strong>:</strong> <em>One of the most significant areas in marketing is consumer position analysis. Retailers can assess the extent of client interest in the goods based on customer pose data. Due to occlusion and left-right similarity difficulties, pose estimation is problematic. We describe a CNN-based solution that includes the body orientation and visibility mask to overcome these two challenges. It provides global information about posture configuration using simple gaits in a retail setting. When a person looks to the right, for example, the left side of his or her body is hidden by the body orientation. In the same way, the person faces the camera, the right shoulder will most likely be on the image's left side. A novel Deep Neural Network design is used to merge body orientation and local joint connections. Second, the visibility mask simulates each joint's occlusion state. Because body orientation is the major source of self-occlusion, it is inextricably tied to it. Detecting an occluding object (such as a shopping cart in a retail setting) might provide give visibility mask prediction clues. Global body position, local joint connections, client mobility, and occluding obstructions are all taken into account in the final advised method. Finally, we run a number of comparison tests to see how effective our technique is.</em> <strong>Objective: </strong><em>This work presents customer posture estimation, and a visibility mask to build a prototype for inner and </em><em>self-occlusion. It also concentrates on local joint connections, global body orientation, and customer mobility.</em> <strong>Methodology: </strong><em>The suggested technique is depicted in its entirety in Figure-2. To figure out which portion of the human picture is concealed, we employ stance markers to identify the viewable areas. The landmarks in the occlusion zone have a lower confidence score when we extract posture landmarks. As a result, it is possible to obtain visible masks incorporating occlusion information. We employ visible signs to assist the hidden individual in three ways. To begin, visible masks are utilized to detect viewable parts and to construct spatial masks that filter noise caused by occlusions.</em> <strong>Findings/Results: </strong><em>The proposed method outperforms to overcome left-right similarity difficulties, the network incorporates body orientation information, and the visibility mark layers are introduced into the network to enhance the efficiency of occluded joints.</em> <strong>Conclusion: </strong><em>For customer pose estimation, A novel architecture using the concepts of Deep Learning is proposed and the occluding object detection clearly provides inter-occlusion by object cues. As a result, local joint connection, the global body orientation, and occluding object and human motion.</em> <strong><em>Paper Type: </em></strong><em>Research article.</em>
31
L, Dr Priya, Poornimathi K, and Dr P. Kumar. "Enhancing Occlusion Handling in Real-Time Tracking Systems through Geometric Mapping and 3D Reconstruction Validation." International Journal of Engineering and Advanced Technology 12, no. 6 (2023): 7–13. http://dx.doi.org/10.35940/ijeat.f4259.0812623.
Full textAbstract:
Object detection is a classic research problem in the area of Computer Vision. Many smart world applications, like, video surveillance or autonomous navigation systems require a high accuracy in pose detection of objects. One of the main challenges in Object detection is the problem of detecting occluded objects and its respective 3D reconstruction. The focus of this paper is inter-object occlusion where two or more objects being tracked occlude each other. A novel algorithm has been proposed for handling object occlusion by using the technique of geometric matching and its 3D projection obtained. The developed algorithm has been tested using sample data and the results are presented.
32
Dr., Priya.L, Poornimathi.K, and P. Kumar Dr. "Enhancing Occlusion Handling in Real-Time Tracking Systems through Geometric Mapping and 3D Reconstruction Validation." International Journal of Engineering and Advanced Technology (IJEAT) 12, no. 6 (2023): 7–13. https://doi.org/10.35940/ijeat.F4259.0812623.
Full textAbstract:
<strong>Abstract: </strong>Object detection is a classic research problem in the area of Computer Vision. Many smart world applications, like, video surveillance or autonomous navigation systems require a high accuracy in pose detection of objects. One of the main challenges in Object detection is the problem of detecting occluded objects and its respective 3D reconstruction. The focus of this paper is inter-object occlusion where two or more objects being tracked occlude each other. A novel algorithm has been proposed for handling object occlusion by using the technique of geometric matching and its 3D projection obtained. The developed algorithm has been tested using sample data and the results are presented.
33
Garg, Aditya. "AI-Powered Yoga Pose Detection and Feedback System." International Journal for Research in Applied Science and Engineering Technology 13, no. 5 (2025): 6224–30. https://doi.org/10.22214/ijraset.2025.70581.
Full textAbstract:
In order to close the gap between conventional yoga practices and contemporary technological breakthroughs, this study introduces a novel AI-driven yoga pose identification and feedback system. With its roots in ancient customs, yoga has gained international recognition for its mental, spiritual, and physical health benefits. However, the individualized, real- time input that is necessary to maintain safe, proper alignment and posture during practice is frequently absent from the contemporary approach to yoga. This study presents a novel AI-powered solution. The solution tackles the major issues with both traditional and digital yoga training, with a reported accuracy of up to 97% under different settings. Users may instantly modify their postures with the platform's real-time feedback features, which lowers the chance of injury and increases the effectiveness of yoga sessions. The technology is made to work on everyday gadgets like laptops and cell phones.
34
Pradhan, Prof M. A., Virendra Tendolkar, Yash Pazade, Vedant Yeole, and Sandesh Rengade. "Yoga Pose Detection and Feedback Generation." International Journal for Research in Applied Science and Engineering Technology 12, no. 11 (2024): 1808–14. http://dx.doi.org/10.22214/ijraset.2024.65309.
Full textAbstract:
Abstract: This study presents an innovative system using computer vision and machine learning for real-time yoga pose detection and feedback. Leveraging advanced algorithms like MediaPipe, OpenPose, and CNNs, it analyzes users' postures through a camera, comparing them with standard poses to provide personalized alignment corrections. This enhances yoga practice by minimizing injuries, improving posture accuracy, and supporting fitness goals. Designed for all skill levels, the system integrates with yoga apps, smart mirrors, and wearables, offering features like progress tracking and adaptive feedback. It demonstrates potential in making yoga safer and more engaging. Future developments could include wearable integration, injury prevention, and customized yoga plans, advancing AI-driven fitness solutions.
35
Patil, Prof P. S. "Yoga Pose Estimation Using YOLO Model." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 07, no. 10 (2023): 1–11. http://dx.doi.org/10.55041/ijsrem26536.
Full textAbstract:
Yoga, an historic exercise for every person and intellectual nicely-being, has gained large recognition in todays world . Monitoring yoga postures is essential for ensuring proper form, but yoga without an yoga professional is not good for person. In this research, we go deeply into the area of video processing ,image processing and deep learning, providing a new approach to yoga pose estimation. Leveraging the modern day YOLO (You Only Look Once) pose version, we suggest an revolutionary answer for real-time yoga pose detection in both images and video. The YOLO structure is customized and adaptative to recognizing and detecting yoga postures, maximizing accuracy and performance. YOLO is a popular deep learning algorithm used for object detection and classification in images and videos. It's known for its speed and efficiency. We inspect the result with in the parameter and also use customize data. We specially design this model for yoga Beginner and Intermediate those who cannot afford personal trainer or not able to mange time. Additionally, we renowned the limitations encountered in the course of our studies, also covering the way for future investigations. Keywords: Pose Estimation,YOLO,KeyPoints Detection,Virtual yoga ,ML models
36
Y U, Pooja. "Yoga Pose Detection and Correction System." International Journal for Research in Applied Science and Engineering Technology 9, no. VII (2021): 2771–79. http://dx.doi.org/10.22214/ijraset.2021.36962.
Full textAbstract:
Activity recognition is useful in many domains. These include biometrics, video -surveillance, human-computer interaction, assisted living, sports arbitration, in-home health monitoring, etc. The health status of an individual can be evaluated and predicted by monitoring and recognizing their activities. Yoga is one such domain that can be used to bring harmony to both body and mind with the help of asana, meditation, and various other breathing techniques. Nowadays in a fast-paced lifestyle, people do not have time to go to yoga classes. Hence, they prefer practicing yoga at home. However, there is a need for a tutor to assess their yoga poses. Hence, the system is presented where the user needs to do the yoga pose which is recognized in real-time video. Then, PoseNet is used to generate key points for the body parts. The identified pose is then compared with the target pose. Based on the comparison status generated by the function, verbal instructions are provided for the user to correct the yoga pose.
37
Ramesh, Richard Sylvester. "Real-Time Facial Recognition and Behaviour Analysis for Workplace Monitoring." INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 05 (2025): 1–9. https://doi.org/10.55041/ijsrem47852.
Full textAbstract:
Abstract - Facial recognition systems have become increasingly valuable in workplace environments where real-time identity verification and behavioural monitoring are essential for ensuring safety, security, and operational efficiency. This paper presents a lightweight and cost-effective facial recognition system designed specifically for workplace monitoring, integrating both identity recognition and behaviour analysis using classical computer vision techniques. The system employs Haar Cascade classifiers for real-time face detection, utilizing OpenCV for image processing and Flask as the backend framework. A live video feed from a camera is processed to recognize individuals and monitor their activity. In addition to identifying faces, the system is capable of detecting specific behavioural patterns, such as inattention or improper handling of materials. When such events are identified, the system logs the behaviour and can issue an alert through a speaker or dashboard notification. A custom-built web dashboard, developed using Dash and Bootstrap, provides real-time visualization of detections, system logs, and analytical charts for better decision-making. The dashboard is responsive, user-friendly, and suitable for deployment in a variety of workplace settings. The proposed solution offers a practical alternative to complex deep learning models, requiring minimal computational resources while still achieving reliable performance. The modular nature of the system also allows for future extensions such as integration with biometric attendance, advanced pose estimation, or cloud-based monitoring. Key Words: Facial Recognition, Behaviour Analysis, Workplace Monitoring, Haar Cascade, Real-Time Detection, OpenCV, Flask Dashboard, Computer Vision
38
Singh, Dashmesh Yashasvi, Sumesh Sood, and Arvind Kalia. "Real-Time Pedestrian Detection with YOLOv7 and Intel MiDaS: A Qualitative Study." International Journal for Research in Applied Science and Engineering Technology 11, no. 9 (2023): 1570–77. http://dx.doi.org/10.22214/ijraset.2023.55885.
Full textAbstract:
Abstract: In the realm of Advanced Driving Assistance Systems (ADAS), the accurate assessment of pedestrian proximity is of paramount importance. This paper introduces a qualitative methodology that integrates YOLOv7-pose for object detection and pose estimation with the MiDaS (Monocular Depth Estimation in Real-Time with Deep Learning) model for monocular depth estimation. The main objective is to qualitatively assess pedestrian proximity to the camera within the ADAS framework. This procedure involves classifying pedestrians as "near" or "far" based on an inverse depth threshold that has been predetermined. In addition, the paper performs a qualitative comparative analysis of the results produced by the MiDaS Small, Hybrid, and Large variants to learn more about the performance of depth estimation in these contexts, particularly in relation to the presence of pedestrians. The evaluation emphasises this approach's qualitative potential for achieving situationally appropriate and context-aware pedestrian proximity assessment. The safety and adaptability of ADAS systems can be improved with the help of such insights, which have numerous applications in robotics, surveillance, and autonomous vehicles.
39
Zhang, Chi, Zhong Yang, Luwei Liao, Yulong You, Yaoyu Sui, and Tang Zhu. "RPEOD: A Real-Time Pose Estimation and Object Detection System for Aerial Robot Target Tracking." Machines 10, no. 3 (2022): 181. http://dx.doi.org/10.3390/machines10030181.
Full textAbstract:
Pose estimation and environmental perception are the fundamental capabilities of autonomous robots. In this paper, a novel real-time pose estimation and object detection (RPEOD) strategy for aerial robot target tracking is presented. The aerial robot is equipped with a binocular fisheye camera for pose estimation and a depth camera to capture the spatial position of the tracked target. The RPEOD system uses a sparse optical flow algorithm to track image corner features, and the local bundle adjustment is restricted in a sliding window. Ulteriorly, we proposed YZNet, a lightweight neural inference structure, and took it as the backbone in YOLOV5 (the state-of-the-art real-time object detector). The RPEOD system can dramatically reduce the computational complexity in reprojection error minimization and the neural network inference process; Thus, it can calculate real-time on the onboard computer carried by the aerial robot. The RPEOD system is evaluated using both simulated and real-world experiments, demonstrating clear advantages over state-of-the-art approaches, and is significantly more fast.
40
Zou, Wei, Yuan Li, Kui Yuan, and De Xu. "Real-time elliptical head contour detection under arbitrary pose and wide distance range." Journal of Visual Communication and Image Representation 20, no. 3 (2009): 217–28. http://dx.doi.org/10.1016/j.jvcir.2009.01.005.
Full text
41
Bedre, Om. "Real Time Yoga Pose Detection Desktop Application using Tkinter with Increased Accuracy and No. of Poses using openPose and LR Machine Learning Algorithm." International Journal for Research in Applied Science and Engineering Technology 12, no. 11 (2024): 1022–24. http://dx.doi.org/10.22214/ijraset.2024.65272.
Full textAbstract:
This work presents a method for precisely identifying different Yoga Pose Assessments using deep learning algorithms. To aid in yoga self-learning, we provide a pose detection-based yoga pose assessment approach in this system. First, the system uses a PC camera and multi-part detection to identify a yoga stance. We also provide an enhanced algorithm for this system's score calculation that works with all positions. Our application's resilience is assessed using various yoga poses in various settings. For yoga detection in real-time movies, a hybrid machine learning model utilizing linear regression is put forth. In this model, features are extracted from each frame's important points derived from Open Pose.
42
Sarvesh Kumar. "Precision-Driven Real-Time Pose Estimation for Therapeutic Interventions: Advanced Heatmap Regression, Reference Video Alignment, and Real-Time Corrective Feedback." Journal of Information Systems Engineering and Management 10, no. 34s (2025): 299–310. https://doi.org/10.52783/jisem.v10i34s.5802.
Full textAbstract:
Accurate movement and posture are essential for effective physical therapy, as improper form can hinder recovery and worsen injuries. This project introduces a real-time human pose estimation system specifically designed for physical therapy, providing precise feedback on body alignment. Utilizing a mod- ified YOLOv8 architecture with custom heatmap regression, the system monitors key joints—particularly the wrist, elbow, and shoulder—vital for upper-body rehabilitation. Initially trained on a combined MPII and COCO 2017 dataset, the model was fine-tuned on a custom dataset of 6,000 images derived from 1,250 video frames under varied lighting conditions, with a 380% augmentation rate to improve robustness across scenarios. Achieving a detection accuracy of 91.61%, the system surpasses widely used models like OpenPose and MediaPipe, which deliver accuracies of 85% and 88%, respectively. With an average frame rate of 27.94 FPS and latency of 19.24 milliseconds per frame, the system provides instant feedback, enabling users to adjust posture in real time. Personalized guidance is offered by calculating the distance between live and reference keypoints, maintaining a mean keypoint detection error under 5 pixels. This real- time corrective feature enhances rehabilitation by empowering users to self-adjust and allowing healthcare providers to track progress effectively. By focusing on physical therapy-specific movements, this system represents a significant advancement in integrating AI-driven solutions into rehabilitation, enhancing both effectiveness and accessibility.
43
Bansal, Roli, Richa Sharma, Priyanshi Jain, Rahul Arora, Sourabh Pal, and Vishal. "DeepYoga: Enhancing Practice with a Real-Time Yoga Pose Recognition System." Engineering, Technology & Applied Science Research 14, no. 6 (2024): 17704–10. https://doi.org/10.48084/etasr.8643.
Full textAbstract:
The adoption of yoga as a holistic wellness practice is increasing throughout the world. However, in the absence of a personalized expert, especially in an online environment, there is a need for reliable and accurate methods for yoga posture recognition. Maintaining correct yoga postures is essential to reap holistic health benefits in the long term and address chronic medical issues. This paper presents DeepYoga, a novel approach to improve posture recognition accuracy with the support of deep learning models. The proposed approach uses a dataset of accurate yoga pose images encompassing five distinct poses. Landmarks extracted from the practitioner's body in the images are then used to train a Convolutional Neural Network (CNN) for accurate pose classification. The trained model is then used to detect yoga poses from real-time videos of yoga practitioners. Then, the system provides users with real-time feedback and visual suggestions, helping them improve physical alignment and reduce the risk of injury. The proposed method achieved an overall high accuracy of 99.02% in pose detection while trying to minimize the use of resources as much as possible to make it more accessible.
44
S, Prof Sharanya P. "Smart Security Systems for Real-Time Human Identification Through GAIT Mechanism." International Journal for Research in Applied Science and Engineering Technology 13, no. 5 (2025): 3619–24. https://doi.org/10.22214/ijraset.2025.70975.
Full textAbstract:
Abstract: The rapid evolution of technological landscapes has necessitated more sophisticated security solutions, with gait analysis emerging as a promising biometric identification technique. This innovative approach leverages individuals' unique walking patterns as a distinctive personal identifier, utilizing advanced computational methods. By integrating Sequential modeling for temporal data processing and MediaPipe Pose for precise pose prediction, the proposed system demonstrates remarkable accuracy and robustness in individual recognition. The methodology capitalizes on the nuanced biomechanical characteristics of human locomotion, transforming walking patterns into a reliable biometric signature. Preliminary research indicates significant potential for future developments, with anticipated enhancements including hybrid biometric integration and multi-person detection capabilities. This approach represents a significant stride in non-invasive, behavioral biometric technologies, offering promising applications across security, surveillance, and personalized authentication domains.
45
Chandrashekar, T. R., K. B. ShivaKumar, A. Srinidhi G, and A. K. Goutam. "PCA Based Rapid and Real Time Face Recognition Technique." COMPUSOFT: An International Journal of Advanced Computer Technology 02, no. 12 (2013): 385–90. https://doi.org/10.5281/zenodo.14613535.
Full textAbstract:
Economical and efficient that is used in various applications is face Biometric which has been a popular form biometric system. Face recognition system is being a topic of research for last few decades. Several techniques are proposed to improve the performance of face recognition system. Accuracy is tested against intensity, distance from camera, and pose variance. Multiple face recognition is another subtopic which is under research now a day. Speed at which the technique works is a parameter under consideration to evaluate a technique. As an example a support vector machine performs really well for face recognition but the computational efficiency degrades significantly with increase in number of classes. Eigen Face technique produces quality features for face recognition but the accuracy is proved to be comparatively less to many other techniques. With increase in use of core processors in personal computers and application demanding speed in processing and multiple face detection and recognition system (for example an entry detection system in shopping mall or an industry), demand for such systems are cumulative as there is a need for automated systems worldwide. In this paper we propose a novel system of face recognition developed with C# .Net that can detect multiple faces and can recognize the faces parallel by utilizing the system resources and the core processors. The system is built around Haar Cascade based face detection and PCA based face recognition system with C#.Net. Parallel library designed for .Net is used to aide to high speed detection and recognition of the real time faces. Analysis of the performance of the proposed technique with some of the conventional techniques reveals that the proposed technique is not only accurate, but also is fast in comparison to other techniques.
46
Sun, Chaojie, Junguo Hu, Qingyue Wang, Chao Zhu, Lei Chen, and Chunmei Shi. "YOLO-BCD: A Lightweight Multi-Module Fusion Network for Real-Time Sheep Pose Estimation." Sensors 25, no. 9 (2025): 2687. https://doi.org/10.3390/s25092687.
Full textAbstract:
The real-time monitoring of animal postures through computer vision techniques has become essential for modern precision livestock management. To overcome the limitations of current behavioral analysis systems in balancing computational efficiency and detection accuracy, this study develops an optimized deep learning framework named YOLOv8-BCD specifically designed for ovine posture recognition. The proposed architecture employs a multi-level lightweight design incorporating enhanced feature fusion mechanisms and spatial-channel attention modules, effectively improving detection performance in complex farm environments with occlusions and variable lighting. Our methodology introduces three technical innovations: (1) Adaptive multi-scale feature aggregation through bidirectional cross-layer connections. (2) Context-aware attention weighting for critical region emphasis. (3) Streamlined detection head optimization for resource-constrained devices. The experimental dataset comprises 1476 annotated images capturing three characteristic postures (standing, lying, and side lying) under practical farming conditions. Comparative evaluations demonstrate significant improvements over baseline models, achieving 91.7% recognition accuracy with 389 FPS processing speed while maintaining 19.2% parameter reduction and 32.1% lower computational load compared to standard YOLOv8. This efficient solution provides technical support for automated health monitoring in intensive livestock production systems, showing practical potential for large-scale agricultural applications requiring real-time behavioral analysis.
47
Krishna, Ram. "Real Time Human Body Posture Analysis Using Deep Learning." International Journal for Research in Applied Science and Engineering Technology 11, no. 5 (2023): 2951–55. http://dx.doi.org/10.22214/ijraset.2023.52099.
Full textAbstract:
Abstract: We present a novel approach for accurately estimating the pose of objects in a low-cost and resource-efficient manner, making it suitable for deployment on embedded systems. Our algorithm comprises of two primary stages: object detection and spatial reconstruction. In the first stage, we employ a Convolutional Neural Network (CNN) called PoseNet for object detection. This approach has proven to be effective in detecting and localizing objects in an image. Next, utilizing stereo correspondences, we 3D reconstruct the spatial coordinates of multiple ORB features within the object's bounding box. This enables us to accurately estimate the position of the object in space. To calculate the final position of the object, we compute a weighted average of the stereo-corresponded key points' spatial coordinates. The weights are proportional to the level of ORB stereo matching, which enables us to obtain a more accurate estimate of the object's position in space. Our algorithm was tested in a calibrated environment, and we compared the results with a deep learning-based method using various datasets. The results show that our approach outperforms existing methods in terms of accuracy, while maintaining a low cost and efficient resource utilization. Our proposed method has several applications, including the quantitative and qualitative analysis of human posture. By analyzing all aspects of a person's posture, we can determine if there are any postural deviations, imbalances, or muscle weaknesses that may be causing pain or discomfort. This information can then be used to develop personalized rehabilitation programs, reducing the risk of injury and enhancing athletic performance. Furthermore, our approach can be used in various assistive technology applications, such as the control of robotic arms for pick-andplace tasks. The low-cost and resource-efficient nature of our algorithm make it ideal for deployment in embedded systems, enabling us to develop affordable and accessible assistive technology solutions. In conclusion, our proposed algorithm provides an accurate, low-cost, and resource-efficient solution for pose estimation, with a wide range of potential applications in human posture analysis, assistive technology, and beyond.
48
Wang, Yifei, Libo Sun, and Wenhu Qin. "OFPoint: Real-Time Keypoint Detection for Optical Flow Tracking in Visual Odometry." Mathematics 13, no. 7 (2025): 1087. https://doi.org/10.3390/math13071087.
Full textAbstract:
Visual odometry (VO), including keypoint detection, correspondence establishment, and pose estimation, is a crucial technique for determining motion in machine vision, with significant applications in augmented reality (AR), autonomous driving, and visual simultaneous localization and mapping (SLAM). For feature-based VO, the repeatability of keypoints affects the pose estimation. The convolutional neural network (CNN)-based detectors extract high-level features from images, thereby exhibiting robustness to viewpoint and illumination changes. Compared with descriptor matching, optical flow tracking exhibits better real-time performance. However, mainstream CNN-based detectors rely on the “joint detection and descriptor” framework to realize matching, making them incompatible with optical flow tracking. To obtain keypoints suitable for optical flow tracking, we propose a self-supervised detector based on transfer learning named OFPoint, which jointly calculates pixel-level positions and confidences. We use the descriptor-based detector simple learned keypoints (SiLK) as the pre-trained model and fine-tune it to avoid training from scratch. To achieve multi-scale feature fusion in detection, we integrate the multi-scale attention mechanism. Furthermore, we introduce the maximum discriminative probability loss term, ensuring the grayscale consistency and local stability of keypoints. OFPoint achieves a balance between accuracy and real-time performance when establishing correspondences on HPatches. Additionally, we demonstrate its effectiveness in VO and its potential for graphics applications such as AR.
49
Jie, Xiaohan, and Ning Liu. "Visual/inertial odometry with tight coupling of multi-bit pose information." Journal of Physics: Conference Series 2492, no. 1 (2023): 012006. http://dx.doi.org/10.1088/1742-6596/2492/1/012006.
Full textAbstract:
Abstract To address the problem that the loosely coupled frame pose scale needs to be initialized manually, making the subsequent algorithm less accurate and less real-time, while the tightly coupled OKVIS does not include closed-loop detection and map building, an adaptive vision/inertial odometry method with tightly coupled multi-bit pose information is proposed, incorporating optimized map points to provide more accurate data for the subsequent algorithm, with repositioning, closed-loop detection and global a complete visual/inertial odometry system with repositioning, closed-loop detection, and global posture map optimization functions. The adaptive vision/inertial odometry with tightly coupled multi-location posture information is experimentally validated to have better real-time performance, accuracy, and robustness than the loosely coupled algorithm.
50
Tong, Xin, Shi Peng, Yufei Guo, and Xuhui Huang. "End-to-End Real-Time Vanishing Point Detection with Transformer." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 6 (2024): 5243–51. http://dx.doi.org/10.1609/aaai.v38i6.28331.
Full textAbstract:
In this paper, we propose a novel transformer-based end-to-end real-time vanishing point detection method, which is named Vanishing Point TRansformer (VPTR). The proposed method can directly regress the locations of vanishing points from given images. To achieve this goal, we pose vanishing point detection as a point object detection task on the Gaussian hemisphere with region division. Considering low-level features always provide more geometric information which can contribute to accurate vanishing point prediction, we propose a clear architecture where vanishing point queries in the decoder can directly gather multi-level features from CNN backbone with deformable attention in VPTR. Our method does not rely on line detection or Manhattan world assumption, which makes it more flexible to use. VPTR runs at an inferring speed of 140 FPS on one NVIDIA 3090 card. Experimental results on synthetic and real-world datasets demonstrate that our method can be used in both natural and structural scenes, and is superior to other state-of-the-art methods on the balance of accuracy and efficiency.