Title :
Research on the detection and tracking technology of moving object in video images
Author :
Qingchang Guo ; Bing Qiao
Author_Institution :
Yichang Testing Technol. Res. Inst., Yichang, China
Abstract :
For accurately detecting and tracking the moving object in the fixed scene, a new algorithm is proposed in the paper. The initial moving region is detected by the inter frame difference method. The accurate moving object is segmented using the background difference method. The tracking features for tracking are extracted based on the segmented object. The moving object is tracked by the mean-shift method. And in order to for accurately tracking the moving object accurately, the background image rebuilt and the tracking feature is corrected real-timely is real-timely rebuilt and tracking feature is real-timely corrected. The effectiveness of the algorithm is verified to be effective through the experiments.
Keywords :
feature extraction; image segmentation; motion estimation; object detection; object tracking; video signal processing; background difference method; background image; fixed scene; interframe difference method; mean-shift method; moving object detection technology; moving object segmentation; moving object tracking technology; moving region detection; tracking feature; tracking feature extraction; video images; Computer vision; Feature extraction; Image segmentation; Object detection; Object tracking; Real-time systems; Target tracking; background reconstruction; mean shift; object tracking;
Conference_Titel :
Mechatronics and Automation (ICMA), 2015 IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-7097-1
DOI :
10.1109/ICMA.2015.7237531