08-16-2017, 09:41 PM
Advantages and disadvantages of two common algorithms frequently used in mobile target detection: the background subtraction method and the frame difference method are analyzed and compared in this document. Then, based on the background subtraction method, a mobile target detection algorithm is proposed. The background image used to process the next frame image is generated by overlaying the current frame image and the current background image with a certain probability. This algorithm makes objects that remain a long time to be a part of the background after a certain period of time, but not be detected as a part of the foreground. The experimental results show that this algorithm can detect moving targets with greater efficiency and precision. Intelligent video surveillance is a new direction for research in the field of computer vision. It uses the computer vision method and detects the motion target in the monitoring scene by automatically analyzing the image sequence by recording the camera. And research on moving target detection and extraction algorithm can be said to be key issues in intelligent video. Its purpose is the detection and extraction of moving targets from the scene of the video image sequence. Therefore, effective detection of moving targets determines system performance. Therefore, this article focuses on key technology in the detection and extraction of moving targets. In this work, first, it has a brief introduction of pre-treatment of video images. Reduce error in image processing after. Second, the article focuses on the comparison of analyzes of the two algorithms: background subtraction and frame difference. Finally, this paper selects based on the background subtraction method to improve it and presents a background based mobile target detection algorithm that has dynamic changes.