Academic literature on the topic 'Opencv'

Machine-learning-based computer vision is increasingly versatile and being leveraged by a wide range of smart devices. Due to the limited performance/energy budget of computing units in smart devices, the careful implementation of computer vision algorithms is critical. In this paper, we analyze the performance bottleneck of two well-known computer vision algorithms for object tracking: object detection and optical flow in the Open-source Computer Vision library (OpenCV). Based on our in-depth analysis of their implementation, we found the current implementation fails to utilize Open Computing Language (OpenCL) accelerators (e.g., GPUs). Based on the analysis, we propose several optimization strategies and apply them to the OpenCL implementation of object tracking algorithms. Our evaluation results demonstrate the performance of the object detection is improved by up to 86% and the performance of the optical flow by up to 10%. We believe our optimization strategies can be applied to other computer vision algorithms implemented in OpenCL.

Abstract: This research introduces a novel method for controlling mouse movement with a real-time camera. Adding more buttons or repositioning the mouse's tracking ball are two common ways. Instead, we recommend that the hardware be redesigned. Our idea is to employ a camera and computer vision technologies to manage mouse tasks (clicking and scrolling), and we demonstrate how it can do all that existing mouse devices can. This project demonstrates how to construct a mouse control system.

<strong>Abstract. </strong>Intensive water quality determination needs to be adjusted with technological developments to meet today's society's needs and increased water pollution due to urbanization. Therefore, early detection is essential for in site water quality determination and as a critical consideration in making health and environmental decisions. OpenCV is a library programming feature for Computer Vision which focuses on extracting information from images in real-time, this can be considered to be potential to measure the pollutant concentration. <strong>Objectives:</strong> This study identify the potential of colorimetry analysis method by using OpenCV as an alternative method for pollutant concentration measurement<strong>. Method and results:</strong> First stage, this study collecting the data of NH3 phenate and Pt-Co CU from the spectrophotometer. The first stage also was including the development of an OpenCV code. Then, the data was collected were processed to get the concentration of NH3 and Pt-Co both using OpenCV and spectrophotometer; factors that influence the Pt-Co sample image measurement process by using OpenCV-Python was analyzed too. Then in the analysis stage, the result of the two measurement method was tested by statistic determine its significant difference. The conclusion found whether OpenCV could be potential to measure the pollutant concentration or not. <strong>Conclusion:</strong> the OpenCV has potential to be use as alternative colorimetry measurement method to determine water pollutant as there is no significant difference in the spectrophotometric method results and the results from OpenCV for Pt-Co sample. Meanwhile, in this study found that the result of NH3 from spectrophotometer is nonlinear different with from OpenCV that is linear. Thus, further research is needed to test the validity of OpenCV method. The factor influence of measurement using OpenCV code is when determining the Region of Interest (ROI) and determining the pixel values for the normalized box filter

For automatic vision systems used in agriculture, the project presents object characteristics analysis using image processing techniques. In agriculture science, automatic object characteristics identification is important for monitoring vast areas of crops, and it detects signs of object characteristics as soon as it occurs on plant leaves. Image content characterization and supervised classifier type neural network are used in the proposed deciding method. Pre-processing, image segmentation, and detection are some of the image processing methods used in this form of decision making. An image data will be rearranged and, if necessary, a region of interest will be selected during preparation. For network training and classification, colour and texture features are extracted from an input. Colour characteristics such as mean and variance in the HSV colour space, as well as texture characteristics such as energy, contrast, homogeneity, and correlation. The device will be trained to automatically identify test images in order to assess object characteristics. With some training samples of that type, an automated classifier NN could be used for classification supported learning in this method. The tangent sigmoid function is used as the kernel function in this network. Finally, the simulated results show that the used network classifier has a low error rate during training and higher classification accuracy. In the previous researches Object detection has been made possible, but in our current research we have attempted to do live Object Detection using OpenCV and also the techniques involved in it.