Relevant bibliographies by topics / Region Proposal Network (RPN)

Contents

  1. Journal articles
  2. Dissertations / Theses
  3. Books
  4. Book chapters
  5. Conference papers
  6. Reports

Academic literature on the topic 'Region Proposal Network (RPN)'

Author: Grafiati
Published: 5 June 2025
Last updated: 15 July 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Region Proposal Network (RPN).'

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.

Journal articles on the topic "Region Proposal Network (RPN)"

1

Liu, Gang, and Chuyi Wang. "A Novel Multi-Scale Feature Fusion Method for Region Proposal Network in Fast Object Detection." International Journal of Data Warehousing and Mining 16, no. 3 (2020): 132–45. http://dx.doi.org/10.4018/ijdwm.2020070107.

Full text
Abstract:
Neural network models have been widely used in the field of object detecting. The region proposal methods are widely used in the current object detection networks and have achieved well performance. The common region proposal methods hunt the objects by generating thousands of the candidate boxes. Compared to other region proposal methods, the region proposal network (RPN) method improves the accuracy and detection speed with several hundred candidate boxes. However, since the feature maps contains insufficient information, the ability of RPN to detect and locate small-sized objects is poor. A novel multi-scale feature fusion method for region proposal network to solve the above problems is proposed in this article. The proposed method is called multi-scale region proposal network (MS-RPN) which can generate suitable feature maps for the region proposal network. In MS-RPN, the selected feature maps at multiple scales are fine turned respectively and compressed into a uniform space. The generated fusion feature maps are called refined fusion features (RFFs). RFFs incorporate abundant detail information and context information. And RFFs are sent to RPN to generate better region proposals. The proposed approach is evaluated on PASCAL VOC 2007 and MS COCO benchmark tasks. MS-RPN obtains significant improvements over the comparable state-of-the-art detection models.
APA, Harvard, Vancouver, ISO, and other styles
2

Zhang, Ximing, Shujuan Luo, and Xuewu Fan. "Proposal-Based Visual Tracking Using Spatial Cascaded Transformed Region Proposal Network." Sensors 20, no. 17 (2020): 4810. http://dx.doi.org/10.3390/s20174810.

Full text
Abstract:
Region proposal network (RPN) based trackers employ the classification and regression block to generate the proposals, the proposal that contains the highest similarity score is formulated to be the groundtruth candidate of next frame. However, region proposal network based trackers cannot make the best of the features from different convolutional layers, and the original loss function cannot alleviate the data imbalance issue of the training procedure. We propose the Spatial Cascaded Transformed RPN to combine the RPN and STN (spatial transformer network) together, in order to successfully obtain the proposals of high quality, which can simultaneously improves the robustness. The STN can transfer the spatial transformed features though different stages, which extends the spatial representation capability of such networks handling complex scenarios such as scale variation and affine transformation. We break the restriction though an easy samples penalization loss (shrinkage loss) instead of smooth L1 function. Moreover, we perform the multi-cue proposals re-ranking to guarantee the accuracy of the proposed tracker. We extensively prove the effectiveness of our proposed method on the ablation studies of the tracking datasets, which include OTB-2015 (Object Tracking Benchmark 2015), VOT-2018 (Visual Object Tracking 2018), LaSOT (Large Scale Single Object Tracking), TrackingNet (A Large-Scale Dataset and Benchmark for Object Tracking in the Wild) and UAV123 (UAV Tracking Dataset).
APA, Harvard, Vancouver, ISO, and other styles
3

Dong, Ruchan, Licheng Jiao, Yan Zhang, Jin Zhao, and Weiyan Shen. "A Multi-Scale Spatial Attention Region Proposal Network for High-Resolution Optical Remote Sensing Imagery." Remote Sensing 13, no. 17 (2021): 3362. http://dx.doi.org/10.3390/rs13173362.

Full text
Abstract:
Deep convolutional neural networks (DCNNs) are driving progress in object detection of high-resolution remote sensing images. Region proposal generation, as one of the key steps in object detection, has also become the focus of research. High-resolution remote sensing images usually contain various sizes of objects and complex background, small objects are easy to miss or be mis-identified in object detection. If the recall rate of region proposal of small objects and multi-scale objects can be improved, it will bring an improvement on the performance of the accuracy in object detection. Spatial attention is the ability to focus on local features in images and can improve the learning efficiency of DCNNs. This study proposes a multi-scale spatial attention region proposal network (MSA-RPN) for high-resolution optical remote sensing imagery. The MSA-RPN is an end-to-end deep learning network with a backbone network of ResNet. It deploys three novel modules to fulfill its task. First, the Scale-specific Feature Gate (SFG) focuses on features of objects by processing multi-scale features extracted from the backbone network. Second, the spatial attention-guided model (SAGM) obtains spatial information of objects from the multi-scale attention maps. Third, the Selective Strong Attention Maps Model (SSAMM) adaptively selects sliding windows according to the loss values from the system’s feedback, and sends the windowed samples to the spatial attention decoder. Finally, the candidate regions and their corresponding confidences can be obtained. We evaluate the proposed network in a public dataset LEVIR and compare with several state-of-the-art methods. The proposed MSA-RPN yields a higher recall rate of region proposal generation, especially for small targets in remote sensing images.
APA, Harvard, Vancouver, ISO, and other styles
4

Rahmani, K., and H. Mayer. "HIGH QUALITY FACADE SEGMENTATION BASED ON STRUCTURED RANDOM FOREST, REGION PROPOSAL NETWORK AND RECTANGULAR FITTING." ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences IV-2 (May 28, 2018): 223–30. http://dx.doi.org/10.5194/isprs-annals-iv-2-223-2018.

Full text
Abstract:
In this paper we present a pipeline for high quality semantic segmentation of building facades using Structured Random Forest (SRF), Region Proposal Network (RPN) based on a Convolutional Neural Network (CNN) as well as rectangular fitting optimization. Our main contribution is that we employ features created by the RPN as channels in the SRF.We empirically show that this is very effective especially for doors and windows. Our pipeline is evaluated on two datasets where we outperform current state-of-the-art methods. Additionally, we quantify the contribution of the RPN and the rectangular fitting optimization on the accuracy of the result.
APA, Harvard, Vancouver, ISO, and other styles
5

Wang, Yanke, Qidan Zhu, Wenchang Nie, and Hong Xiao. "Do tracking by clustering anchors output from region proposal network." MATEC Web of Conferences 246 (2018): 03006. http://dx.doi.org/10.1051/matecconf/201824603006.

Full text
Abstract:
Most existing clustering algorithms suffer from the computation of similarity function and the representation of each object. In this paper, we propose a clustering tracker based on region proposal network (RPN-C) to do tracking by clustering anchors output by region proposal network into potential centers. We first cut off the second part of Faster RCNN and then cast clustering algorithms in feature space of anchors, including K-Means, mean shift and density peak clustering strategy in terms of anchors’ centroid and scale information. Without fully connected layers, the RPN-C tracker can lower the computational cost up to 60% and still, it can effectively maintain an accurate prediction for the localization in next frame. To evaluate the robustness of this tracker, we establish a dataset containing over 2000 training images and 7 testing sequences of 8 kinds of fruits. The experimental results on our own datasets demonstrate that the proposed tracker performs excellently both in location of object and the decision of scale and has a strong advantage of stability in the context of occlusion and complicated background.
APA, Harvard, Vancouver, ISO, and other styles
6

J, Srilatha, S. Subashini T, and Vaidehi K. "Solid Waste Detection and Recognition using Faster RCNN." Indian Journal of Science and Technology 16, no. 42 (2023): 3778–85. https://doi.org/10.17485/IJST/v16i42.2005.

Full text
Abstract:
Abstract <strong>Objective:</strong>&nbsp;To develop a two-stage object detection method based on convolutional neural networks (CNNs) to identify and classify solid waste, contributing to the creation of intelligent systems for society.&nbsp;<strong>Methods:</strong>&nbsp;The study utilizes a base network, ResNet 101, to generate convolution feature maps. In the first stage, a Region Proposal Network (RPN) is created on top of these convolution features, producing 256-dimensional feature vectors, objectness scores, and bounding rectangles for different anchor boxes. In the next stage, the region proposals are used to train a softmax layer and regressor, enabling the classification and localization of five types of solid waste, namely cardboard, glass, metal, paper and plastic.&nbsp;<strong>Findings:</strong>&nbsp;The proposed Faster RCNN demonstrates nearly real-time object detection rates. Experimental results reveal that the Faster RCNN with ResNet 101 and RPN achieves an accuracy of 96.7%, outperforming the Faster RCNN with a simple CNN, which achieves an accuracy of 86.7%.&nbsp;<strong>Novelty:</strong>&nbsp;Unlike traditional R-CNN, which relies on computationally inefficient selective search, the proposed Faster RCNN employs RPN, a small neural network sliding on the last convolution layer's feature map, predicting object presence and bounding boxes. This approach significantly improves efficiency compared to the exhaustive examination in R-CNN's selective search. <strong>Keywords</strong>: Object Detection, RCNN, Fast RCNN, Faster RCNN, RPN, ROI pooling
APA, Harvard, Vancouver, ISO, and other styles
7

He, Dongfang, Jiajun Wen, and Zhihui Lai. "Textile Fabric Defect Detection Based on Improved Faster R-CNN." AATCC Journal of Research 8, no. 1_suppl (2021): 82–90. http://dx.doi.org/10.14504/ajr.8.s1.11.

Full text
Abstract:
To identify and locate industrial textile defects accurately, this study proposes a textile detection model based on a convolution neural network (CNN) known as Faster R-CNN. First, a textile defect feature map was extracted by ResNet-101 deep convolution network. Faster R-CNN only extracts features from the last layer of the feature map, which leads to a loss of low-level location information. The proposed method adds the feature pyramid network (FPN) to the network architecture to make an independent prediction for each level in the feature extraction stage. The extracted feature map is input into the regional proposal network, among which the overlapping regional proposals are suppressed. The proposed improved Faster R-CNN model with Region Proposal Network (RPN), Soft Non-Maximum Suppression (NMS), and Region of Interest (ROI) Align can achieve a detection accuracy of 98% and an mean of Average Precision (mAP) of 85%, which is more competitive than the state-of-the-art deep learning-based object detection algorithms.
APA, Harvard, Vancouver, ISO, and other styles
8

Wang, Rujing, Lin Jiao, Chengjun Xie, Peng Chen, Jianming Du, and Rui Li. "S-RPN: Sampling-balanced region proposal network for small crop pest detection." Computers and Electronics in Agriculture 187 (August 2021): 106290. http://dx.doi.org/10.1016/j.compag.2021.106290.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Li, Danhua, Xiaofeng Di, Xuan Qu, Yunfei Zhao, and Honggang Kong. "Deep Convolutional Neural Network for Pedestrian Detection with Multi-Levels Features Fusion." MATEC Web of Conferences 232 (2018): 01061. http://dx.doi.org/10.1051/matecconf/201823201061.

Full text
Abstract:
Pedestrian detection aims to localize and recognize every pedestrian instance in an image with a bounding box. The current state-of-the-art method is Faster RCNN, which is such a network that uses a region proposal network (RPN) to generate high quality region proposals, while Fast RCNN is used to classifiers extract features into corresponding categories. The contribution of this paper is integrated low-level features and high-level features into a Faster RCNN-based pedestrian detection framework, which efficiently increase the capacity of the feature. Through our experiments, we comprehensively evaluate our framework, on the Caltech pedestrian detection benchmark and our methods achieve state-of-the-art accuracy and present a competitive result on Caltech dataset.
APA, Harvard, Vancouver, ISO, and other styles
10

Rana, Aayush Jung, and Yogesh S. Rawat. "SSA2D: Single Shot Actor-Action Detection in Videos (Student Abstract)." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 18 (2021): 15875–76. http://dx.doi.org/10.1609/aaai.v35i18.17934.

Full text
Abstract:
We propose a single-shot approach for actor-action detection in videos. The existing approaches use a two-step process, which rely on Region Proposal Network (RPN), where the action is estimated based on the detected proposals followed by post-processing such as non-maximal suppression. While effective in terms of performance, these methods pose limitations in scalability for dense video scenes with a high memory requirement for thousand of proposals, which leads to slow processing time. We propose SSA2D, a unified end-to-end deep network, which performs joint actor-action detection in a single-shot without the need of any proposals and post-processing, making it memory as well as time efficient.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "Region Proposal Network (RPN)"

1

Grossman, Mikael. "Proposal networks in object detection." Thesis, KTH, Matematisk statistik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-241918.

Full text
Abstract:
Locating and extracting useful data from images is a task that has been revolutionized in the last decade as computing power has risen to such a level to use deep neural networks with success. A type of neural network that uses the convolutional operation called convolutional neural network (CNN) is suited for image related tasks. Using the convolution operation creates opportunities for the network to learn their own filters, that previously had to be hand engineered. For locating objects in an image the state-of-the-art Faster R-CNN model predicts objects in two parts. Firstly, the region proposal network (RPN) extracts regions from the picture where it is likely to find an object. Secondly, a detector verifies the likelihood of an object being in that region.For this thesis, we review the current literature on artificial neural networks, object detection methods, proposal methods and present our new way of generating proposals. By replacing the RPN with our network, the multiscale proposal network (MPN), we increase the average precision (AP) with 12% and reduce the computation time per image by 10%.<br>Lokalisering av användbar data från bilder är något som har revolutionerats under det senaste decenniet när datorkraften har ökat till en nivå då man kan använda artificiella neurala nätverk i praktiken. En typ av ett neuralt nätverk som använder faltning passar utmärkt till bilder eftersom det ger möjlighet för nätverket att skapa sina egna filter som tidigare skapades för hand. För lokalisering av objekt i bilder används huvudsakligen Faster R-CNN arkitekturen. Den fungerar i två steg, först skapar RPN boxar som innehåller regioner där nätverket tror det är störst sannolikhet att hitta ett objekt. Sedan är det en detektor som verifierar om boxen är på ett objekt .I denna uppsats går vi igenom den nuvarande litteraturen i artificiella neurala nätverk, objektdektektering, förslags metoder och presenterar ett nytt förslag att generera förslag på regioner. Vi visar att genom att byta ut RPN med vår metod (MPN) ökar vi precisionen med 12% och reducerar tiden med 10%.
APA, Harvard, Vancouver, ISO, and other styles
2

Broyelle, Antoine. "Automated Pulmonary Nodule Detection on Computed Tomography Images with 3D Deep Convolutional Neural Network." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-231930.

Full text
Abstract:
Object detection on natural images has become a single-stage end-to-end process thanks to recent breakthroughs on deep neural networks. By contrast, automated pulmonary nodule detection is usually a three steps method: lung segmentation, generation of nodule candidates and false positive reduction. This project tackles the nodule detection problem with a single stage modelusing a deep neural network. Pulmonary nodules have unique shapes and characteristics which are not present outside of the lungs. We expect the model to capture these characteristics and to only focus on elements inside the lungs when working on raw CT scans (without the segmentation). Nodules are small, distributed and infrequent. We show that a well trained deep neural network can spot relevantfeatures and keep a low number of region proposals without any extra preprocessing or post-processing. Due to the visual nature of the task, we designed a three-dimensional convolutional neural network with residual connections. It was inspired by the region proposal network of the Faster R-CNN detection framework. The evaluation is performed on the LUNA16 dataset. The final score is 0.826 which is the average sensitivity at 0.125, 0.25, 0.5, 1, 2, 4, and 8 false positives per scan. It can be considered as an average score compared to other submissions to the challenge. However, the solution described here was trained end-to-end and has fewer trainable parameters.<br>Objektdetektering i naturliga bilder har reducerates till en enstegs process tack vare genombrott i djupa neurala nätverk. Automatisk detektering av pulmonella nodulärer är vanligtvis ett trestegsproblem: segmentering av lunga, generering av nodulärkandidater och reducering av falska positiva utfall. Det här projektet tar sig an nodulärdetektering med en enstegsmodell med hjälp av ett djupt neuralt nätverk. Pulmonella nodulärer har unika karaktärsdrag som inte finns utanför lungorna. Modellen förväntas fånga dessa drag och enbart fokusera på element inuti lungorna när den arbetar med datortomografibilder. Nodulärer är små och glest föredelade. Vi visar att ett vältränat nätverk kan finna relevanta särdrag samt föreslå ett lågt antal intresseregioner utan extra för- eller efter- behandling. På grund av den visuella karaktären av det här problemet så designade vi ett tredimensionellt s.k. convolutional neural network med residualkopplingar. Projektet inspirerades av Faster R-CNN, ett nätverk som utmärker sig i sin förmåga att detektera intresseregioner. Nätverket utvärderades på ett dataset vid namn LUNA16. Det slutgiltiga nätverket testade 0.826, vilket är genomsnittlig sensitivitet vid 0.125, 0.25, 0.5, 1, 2, 4, och 8 falska positiva per utvärdering. Detta kan anses vara genomsnittligt jämfört med andra deltagande i tävlingen, men lösningen som föreslås här är en enstegslösning som utför detektering från början till slut och har färre träningsbara parametrar.<br>La détection d’objets sur les images naturelles est devenue au fil du temps un processus réalisé de bout en bout en une seule étape grâce aux évolutions récentes des architectures de neurones artificiels profonds. En revanche, la détection automatique de nodules pulmonaires est généralement un processus en trois étapes : la segmentation des poumons (pré-traitement), la génération de zones d’intérêt (modèle) et la réduction des faux positifs (post-traitement). Ce projet s’attaque à la détection des nodules pulmonaires en une seule étape avec un réseau profond de neurones artificiels. Les nodules pulmonaires ont des formes et des structures uniques qui ne sont pas présentes en dehors de cet organe. Nous nous attendons à ce qu’un modèle soit capable de capturer ces caractéristiques et de se focaliser uniquement sur les éléments à l’intérieur des poumons alors même qu’il reçoit des images brutes (sans segmentation des poumons). Les nodules sont petits, peu fréquents et répartis aléatoirement. Nous montrons qu’un modèle correctement entraîné peut repérer les éléments caractéristiques des nodules et générer peu de localisations sans pré-traitement ni post-traitement. Du fait de la nature visuelle de la tâche, nous avons développé un réseau neuronal convolutif tridimensionnel. L’architecture utilisée est inspirée du méta-algorithme de détection Faster R-CNN. L’évaluation est réalisée avec le jeu de données du challenge LUNA16. Le score final est de 0.826 qui représente la sensibilité moyenne pour les valeurs de 0.125, 0.25, 0.5, 1, 2, 4 et 8 faux positifs par scanner. Il peut être considéré comme un score moyen comparé aux autres contributions du challenge. Cependant, la solution décrite montre la faisabilité d’un modèle en une seule étape, entraîné de bout en bout. Le réseau comporte moins de paramètres que la majorité des solutions.
APA, Harvard, Vancouver, ISO, and other styles
3

Lin, Chia-Ho, and 林家禾. "Memory-Efficient Hardware-Friendly Algorithm of Region Proposal Network for Human-Object Interaction." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/tctc6z.

Full text
Abstract:
碩士<br>國立臺灣大學<br>電子工程學研究所<br>107<br>Growth of wearable devices in recent years have facilitated a series of advanced applications in computer vision, which usually involves recognizing human activity and manipulated objects. The CNN-based accelerators proposed in recent years have facilitate the progress in human-object interaction system. However, lack of robust and flexible architecture for object detection makes it difficult to build a reliable system for egocentric applications. Besides, the detector requires real-time response under high-resolution videos with low power consumption to fit in applications in egocentric view. This thesis introduces a hardware-friendly algorithm and a hardware architecture for Region Proposal Network as video representations. The Region Proposal Network is a light-weight deep neural network for detection, which is easy to couple with network models of different size to balance between accuracy and complexity. Besides, it has been shown to benefit egocentric action recognition in recent works. Our goal is to achieve real-time computing for applications related to real-world egocentric action recognition. First, we propose a hardware-friendly algorithm, including anchor reduction and patch-based RoI pooling, to reduce resource requirement. Based on these techniques, we further design an architecture, including sparsity-aware convolution and channel-wise zero-skipping, to achieve high throughput, low memory cost and low bandwidth. We are the first to propose a hardware-friendly algorithm and architecture for Region Proposal Network. With the chip&apos;&apos;s small area, low memory cost, and high throughput, it can be applied to many applications on mobile devices, or combined with deep neural network to implement state-of-the-art systems for real-time action recognition.
APA, Harvard, Vancouver, ISO, and other styles
4

Shih, Kuan-Hung, and 施冠宏. "Real-Time Object Detection via Pruning and Concatenated Multi-Feature Assisted Region Proposal Network." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/d7d2x3.

Full text
Abstract:
碩士<br>國立清華大學<br>資訊工程學系所<br>107<br>Object detection is an important research area in the field of computer vision. Its purpose is to find all objects in an image and recognize the class of each object. Since the development of deep learning, an increasing number of studies have ap- plied deep learning in object detection and have achieved successful results. For object detection, there are two types of network architectures: one-stage and two- stage. This study is based on the widely-used two-stage architecture, called Faster R-CNN, and our goal is to improve the inference time to achieve real-time speed without losing accuracy. First, we use pruning to reduce the number of parameters and the amount of computation, which is expected to reduce accuracy as a result. Therefore, we propose a multi-feature assisted region proposal network composed of assisted multi-feature concatenation and a reduced region proposal network to improve accuracy. Assisted multi-feature concatenation combines feature maps from dif- ferent convolutional layers as inputs for a reduced region proposal network. With our proposed method, the network can find regions of interest (ROIs) more accu- rately. Thus, it compensates for loss of accuracy due to pruning. Finally, we use ZF-Net and VGG16 as backbones, and test the network on the PASCAL VOC 2007 dataset. The results show that we can compress ZF-Net from 227 MB to 45 MB and save 66% of computation. We can also compress VGG16 from 523 MB to 144 MB and save 77% of computation. Consequently, the inference speed is 40 FPS for ZF-Net and 27 FPS for VGG16. With the significant compression rates, the accuracies are 60.2% mean average precision (mAP) and 69.1% mAP for ZF-Net and VGG16, respectively.
APA, Harvard, Vancouver, ISO, and other styles

Books on the topic "Region Proposal Network (RPN)"

1

Shain, A. Richard. Boston Heritage Network: Business proposal : confidential information. A.R. Shain, 1994.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
2

CONVERDS, the collaborative network for vegetable research and development in the southern African region: Joint project proposal. SACCAR, 1991.

Find full text
APA, Harvard, Vancouver, ISO, and other styles

Book chapters on the topic "Region Proposal Network (RPN)"

1

Bhonde, Aparna, Kaivalya Londhe, Shubham Jadhav, Saahil Jawale, and Piyush Jawale. "Handwritten Text Recognition Using Region Proposal Network (RPN)." In Studies in Smart Technologies. Springer Nature Singapore, 2025. https://doi.org/10.1007/978-981-97-9132-3_17.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Li, Wenkai, and Andy Song. "UFO RPN: A Region Proposal Network for Ultra Fast Object Detection." In Lecture Notes in Computer Science. Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-97546-3_50.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Cheng, Shuishui, Qingxuan Shi, Nick Jin Sean Lim, and Albert Bifet. "AA-RPN: Adaptive Anchor-Based Region Proposal Network for Remote Sensing Object Detection." In Lecture Notes in Computer Science. Springer Nature Singapore, 2025. https://doi.org/10.1007/978-981-96-6596-9_10.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Chen, Chengpeng, Xinhang Song, and Shuqiang Jiang. "Focal Loss for Region Proposal Network." In Pattern Recognition and Computer Vision. Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-030-03335-4_32.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Wang, Rujing, Lin Jiao, and Kang Liu. "Sampling-Balanced Region Proposal Network for Pest Detection." In Deep Learning for Agricultural Visual Perception. Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-99-4973-1_4.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Tang, Peng, Xinggang Wang, Angtian Wang, et al. "Weakly Supervised Region Proposal Network and Object Detection." In Computer Vision – ECCV 2018. Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-030-01252-6_22.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Cui, Shugang, Shu Tian, and Xucheng Yin. "Combined Correlation Filters with Siamese Region Proposal Network for Visual Tracking." In Neural Information Processing. Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-36711-4_12.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Han, Guangxing, Xuan Zhang, and Chongrong Li. "Revisiting Faster R-CNN: A Deeper Look at Region Proposal Network." In Neural Information Processing. Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-70090-8_2.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Chu, Mengdie, Shuai Wu, Yifan Gu, and Yong Xu. "Rich Features and Precise Localization with Region Proposal Network for Object Detection." In Biometric Recognition. Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-69923-3_65.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Liu, Jun, and PengFei Li. "A Mask R-CNN Model with Improved Region Proposal Network for Medical Ultrasound Image." In Intelligent Computing Theories and Application. Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-319-95933-7_4.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "Region Proposal Network (RPN)"

1

Han, Feiteng, Ming Xue, Yongqiang Liu, et al. "Receptive-field adaptive region proposal network for accurate pedestrian detection." In 4th International Conference on Automation Control. Algorithm and Intelligent Bionics, edited by Jing Na and Shuping He. SPIE, 2024. http://dx.doi.org/10.1117/12.3040216.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Brazil, Garrick, and Xiaoming Liu. "M3D-RPN: Monocular 3D Region Proposal Network for Object Detection." In 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, 2019. http://dx.doi.org/10.1109/iccv.2019.00938.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Cho, MyeongAh, Tae-young Chung, Hyeongmin Lee, and Sangyoun Lee. "N-RPN: Hard Example Learning For Region Proposal Networks." In 2019 IEEE International Conference on Image Processing (ICIP). IEEE, 2019. http://dx.doi.org/10.1109/icip.2019.8803519.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Qing, Chen, Tong Xiao, Shuzhuang Zhang, and Peng Li. "Region Proposal Networks (RPN) Enhanced Slicing for Improved Multi-Scale Object Detection." In 2024 7th International Conference on Communication Engineering and Technology (ICCET). IEEE, 2024. http://dx.doi.org/10.1109/iccet62255.2024.00018.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Liu, Yubo, Guangzhi Liao, Lizhi Xiao, et al. "Automatic Fracture Segmentation and Detection From Image Logging Using Mask R-CNN." In 2022 SPWLA 63rd Annual Symposium. Society of Petrophysicists and Well Log Analysts, 2022. http://dx.doi.org/10.30632/spwla-2022-0115.

Full text
Abstract:
Image logs provide a wide range of information about petrophysical properties and geological features of reservoirs. The identification of fractures by image logging is very important for the precise prediction of production and the accurate evaluation of oil and gas. However, the interpretations of underlying features from fracture occurrences, which could be crucial for experts in fields, are relatively rare. Nowadays, deep learning networks, used to learn representations of image with diverse levels of abstraction, could perform well for understanding the intrinsic features of image log data. In this study, we proposed a deep learning method called Mask R-CNN to recognize the features of fractures based on the datasets of image logs. This deep net detects and segments each fracture individually by focusing on local information of image logs. It provides a novel way for experts and researchers to identify and quantify the fractures precisely and then calculate parameters of fractures efficiently. The applied model contains two parallel branches to recognize and segment fractures respectively. The first workflow, following the idea of Faster R-CNN, is used to track the positions of fracture through the Region Proposal Networks (RPN) and two regression networks. The other branch performs a Fully Connected Network (FCN) to implement up-sampling and output the mask of fractures from image log data. These branches both accept inputs which are based on the same feature maps via the modified Feature Pyramid Networks (Feature Pyramid Networks). The FPN is used to extract features with various scales. To obtain dataset with high quality, we annotated the fracture by manual and implemented data augmentations. All kinds of labeled fractures are marked as mask images in which the pixels 0, 1, 2 and 3 stand for background, induced fractures natural fractures and bedding separately. By the mask image with pixel-wise labels, the dataset with 518 images was used in this paper. Overall, the proposed method in this paper achieves ideal performance to detect the fractures and beddings with the average precision of over 75%. Based on the identification result, we calculate parameters of fractures, such as dip angle. As a consequence, the method in this work shows its potential for identifying all the significant information in borehole through image log data.
APA, Harvard, Vancouver, ISO, and other styles
6

Zhao, Xin, Liufang Sang, Guiguang Ding, Yuchen Guo, and Xiaoming Jin. "Grouping Attribute Recognition for Pedestrian with Joint Recurrent Learning." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/441.

Full text
Abstract:
Pedestrian attributes recognition is to predict attribute labels of pedestrian from surveillance images, which is a very challenging task for computer vision due to poor imaging quality and small training dataset. It is observed that semantic pedestrian attributes to be recognised tend to show semantic or visual spatial correlation. Attributes can be grouped by the correlation while previous works mostly ignore this phenomenon. Inspired by Recurrent Neural Network (RNN)'s super capability of learning context correlations, this paper proposes an end-to-end Grouping Recurrent Learning (GRL) model that takes advantage of the intra-group mutual exclusion and inter-group correlation to improve the performance of pedestrian attribute recognition. Our GRL method starts with the detection of precise body region via Body Region Proposal followed by feature extraction from detected regions. These features, along with the semantic groups, are fed into RNN for recurrent grouping attribute recognition, where intra group correlations can be learned. Extensive empirical evidence shows that our GRL model achieves state-of-the-art results, based on pedestrian attribute datasets, i.e. standard PETA and RAP datasets.
APA, Harvard, Vancouver, ISO, and other styles
7

Lei, Jiaming, Jielong Guo, Hui Yu, Hai Lan, Chao Li, and Zhiying Zhang. "Radar-RPN: Accurate Region Proposal with mmWave Radar in 3D Detection." In 2022 4th International Conference on Frontiers Technology of Information and Computer (ICFTIC). IEEE, 2022. http://dx.doi.org/10.1109/icftic57696.2022.10075246.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Huang, Zili, Shinji Watanabe, Yusuke Fujita, et al. "Speaker Diarization with Region Proposal Network." In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020. http://dx.doi.org/10.1109/icassp40776.2020.9053760.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Cury, Hachid Habib, Evandro Leonardo Silva Teixeira, and Rafael Rodrigues Silva. "Low-Level Data Fusion between Camera and Automotive RADAR for Vehicle and Pedestrian Detection Using nuScenes Database." In SAE Brasil 2024 Congress. SAE International, 2024. https://doi.org/10.4271/2024-36-0064.

Full text
Abstract:
&lt;div class="section abstract"&gt;&lt;div class="htmlview paragraph"&gt;Autonomous driving technology has indeed become a focal point of research globally, with significant efforts directed towards enhancing its key components: environment perception, vehicle localization, path planning, and motion control. These components work together to enable autonomous vehicles to navigate complex environments safely and efficiently. Among these components, environment perception stands out as critical, as it involves the robust, real-time detection of targets on the road. This process relies heavily on the integration of various sensors, making data fusion an indispensable tool in the early stages of automation. Sensor fusion between the camera and RADAR (Radio Detection and Ranging) has advantages because they are complementary sensors, where fusion combines the high lateral resolution from the vision system with the robustness in the face of adverse weather conditions and light invulnerability of RADAR, as well as having a lower production cost compared to the LiDAR (Light Detection and Ranging) sensor. Given the importance of sensor fusion for automated driving, this paper examines the low-level sensory fusion method that uses RADAR detection to generate Regions of Interest (ROIs) in the camera coordinate system. To do so, it was selected a fusion algorithm based on RRPN (Radar Region Proposal Network), which combines RADAR and camera data, and compared it to Faster R-CNN, which uses only camera data. Our goal was to study the advantages and limitations of the proposed method. We explored the NuScenes database to determine the best aspect ratios for different object sizes and modified the RRPN algorithm to generate more effective anchors. For training, we used camera and frontal RADAR data from the NuScenes database. The COCO dataset metrics under three different temporal conditions: day, night, and rain was used to evaluate the proposed models.&lt;/div&gt;&lt;/div&gt;
APA, Harvard, Vancouver, ISO, and other styles
10

Tajrean, Shaharat, and Mohammad Abu Yousuf. "Handwritten Bengali Number Detection using Region Proposal Network." In 2019 International Conference on Bangla Speech and Language Processing (ICBSLP). IEEE, 2019. http://dx.doi.org/10.1109/icbslp47725.2019.202049.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Reports on the topic "Region Proposal Network (RPN)"

1

Virtucio, Michael, Barbaros Cetiner, Bingyu Zhao, Kenichi Soga, and Erturgul Taciroglu. A Granular Framework for Modeling the Capacity Loss and Recovery of Regional Transportation Networks under Seismic Hazards: A Case Study on the Port of Los Angeles. Pacific Earthquake Engineering Research Center, University of California, Berkeley, CA, 2024. http://dx.doi.org/10.55461/hxhg3206.

Full text
Abstract:
Earthquakes, being both unpredictable and potentially destructive, pose great risks to critical infrastructure systems like transportation. It becomes crucial, therefore, to have both a fine-grained and holistic understanding of how the current state of a transportation system would fare during hypothetical hazard scenarios. This paper introduces a synthesis approach to assessing the impacts of earthquakes by coupling an image-based structure-and-site-specific bridge fragility generation methodology with regional-scale traffic simulations and economic loss prediction models. The proposed approach’s use of context-rich data such as OpenStreetMap and Google Street View enables incorporating information that is abstracted in standard loss analysis tools like HAZUS in order to construct nonlinear bridge models and corresponding fragility functions. The framework uses a semi-dynamic traffic assignment model run on a regional traffic network that includes all freeways and local roads (1,444,790 edges) and outputs traffic volume on roads before and after bridge closures due to an earthquake as well as impacts to individual trips (42,056,426 trips). The combination of these models enables granularity, facilitating a bottom-up approach to estimating costs incurred solely due to physical damage to the transportation network. As a case study, the proposed framework is applied to the road network surrounding the Port of Los Angeles---an infrastructure of crucial importance---for assessing resilience and losses at a high resolution. It is found that the port area is disproportionately impacted in the hypothetical earthquake scenario, and delays in bridge repair can lead to a 50% increase in costs.
APA, Harvard, Vancouver, ISO, and other styles
2

Chandrasekhar, C. P. The Long Search for Stability: Financial Cooperation to Address Global Risks in the East Asian Region. Institute for New Economic Thinking Working Paper Series, 2021. http://dx.doi.org/10.36687/inetwp153.

Full text
Abstract:
Forced by the 1997 Southeast Asian crisis to recognize the external vulnerabilities that openness to volatile capital flows result in and upset over the post-crisis policy responses imposed by the IMF, countries in the sub-region saw the need for a regional financial safety net that can pre-empt or mitigate future crises. At the outset, the aim of the initiative, then led by Japan, was to create a facility or design a mechanism that was independent of the United States and the IMF, since the former was less concerned with vulnerabilities in Asia than it was in Latin America and that the latter’s recommendations proved damaging for countries in the region. But US opposition and inherited geopolitical tensions in the region blocked Japan’s initial proposal to establish an Asian Monetary Fund, a kind of regional IMF. As an alternative, the ASEAN+3 grouping (ASEAN members plus China, Japan and South Korea) opted for more flexible arrangements, at the core of which was a network of multilateral and bilateral central bank swap agreements. While central bank swap agreements have played a role in crisis management, the effort to make them the central instruments of a cooperatively established regional safety net, the Chiang Mai Initiative, failed. During the crises of 2008 and 2020 countries covered by the Initiative chose not to rely on the facility, preferring to turn to multilateral institutions such as the ADB, World Bank and IMF or enter into bilateral agreements within and outside the region for assistance. The fundamental problem was that because of an effort to appease the US and the IMF and the use of the IMF as a foil against the dominance of a regional power like Japan, the regional arrangement was not a real alternative to traditional sources of balance of payments support. In particular, access to significant financial assistance under the arrangement required a country to be supported first by an IMF program and be subject to the IMF’s conditions and surveillance. The failure of the multilateral effort meant that a specifically Asian safety net independent of the US and the IMF had to be one constructed by a regional power involving support for a network of bilateral agreements. Japan was the first regional power to seek to build such a network through it post-1997 Miyazawa Initiative. But its own complex relationship with the US meant that its intervention could not be sustained, more so because of the crisis that engulfed Japan in 1990. But the prospect of regional independence in crisis resolution has revived with the rise of China as a regional and global power. This time both economics and China’s independence from the US seem to improve prospects of successful regional cooperation to address financial vulnerability. A history of tensions between China and its neighbours and the fear of Chinese dominance may yet lead to one more failure. But, as of now, the Belt and Road Initiative, China’s support for a large number of bilateral swap arrangements and its participation in the Regional Comprehensive Economic Partnership seem to suggest that Asian countries may finally come into their own.
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'Region Proposal Network (RPN)' for particular source types:
Journal articles
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography