Research on Moving Object Detection and Matching Technology in Multi-Angle Monitoring Video

Prospect detection, extraction and tracking matching of moving objects in surveillance video has always been an important research content in the field of computer vision. It has important practical value in intelligent traffic supervision, video security monitoring, navigation and other aspects. In this paper, the detection and extraction of the same foreground moving object and the matching label in multi-view surveillance videos are studied. A multi-view foreground matching model based on HOG detection and system clustering is established by using background subtraction method, HOG feature detection and least squares of deviations in system clustering. The feature matching of the same foreground object is carried out, thus realizing different foreground objects. Recognition and matching of the same foreground object in multi-angle video. The experimental results show that the model can detect, extract and match foreground moving objects effectively by simultaneously shooting multiple surveillance videos from different angles near the same location.

[1]  Massimo Piccardi,et al.  Background subtraction techniques: a review , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[2]  Oscar Déniz-Suárez,et al.  Face recognition using Histograms of Oriented Gradients , 2011, Pattern Recognit. Lett..

[3]  Chi Qin Lai,et al.  A review on pedestrian detection techniques based on Histogram of Oriented gradient feature , 2014, 2014 IEEE Student Conference on Research and Development.

[4]  Fabio Tozeto Ramos,et al.  An integrated probabilistic model for scan-matching, moving object detection and motion estimation , 2010, 2010 IEEE International Conference on Robotics and Automation.

[5]  Yongjun Zhang,et al.  An Enhanced Histogram of Oriented Gradients for Pedestrian Detection , 2015, IEEE Intelligent Transportation Systems Magazine.

[6]  Shang-Hong Lai,et al.  Adaptive Foreground Object Extraction for Real-Time Video Surveillance with Lighting Variations , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[7]  Marc Van Droogenbroeck,et al.  ViBe: A Universal Background Subtraction Algorithm for Video Sequences , 2011, IEEE Transactions on Image Processing.