Moving Object Detection Based on OpenCV and Embedded ZedBoard
LI Zhe
ZHANG Ying
Abstract：In order to solve the problem that the disk storage is too large and the search for suspicious dynamic objects is not easy in the past,this paper builds an embedded image processing platform based on OpenCV at ZedBoard development board. By using USB camera to collect the video image and improving the the Pyramid Lucas-kanade optical flow method in OpenCV,the pur-pose of this paper is to detect and track the moving objects in the target area and also save them as video files without writing to the static background. Experimental results show that the system can effectively monitor moving objects in the target area and store them,not only reducing the storage capacity of video recording,but also having certain feasibility. The system of this paper has the corresponding reference value and the practical significance to the intelligent monitoring.
Keywords：ZedBoardembedded LinuxOpenCVintelligent monitoringPyramid Lucas-kanade of optical flow
Publication Date：2017-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 2152-2156,2162 )