Title :
Moving target tracking based on adaptive background subtraction and improved camshift algorithm
Author :
Xu, Gang ; Zhao, Dong ; Zhou, Qi ; Huang, Ding
Abstract :
Object tracking is one of the most important techniques in digital image processing. Considering the weakness and shortage of traditional moving target tracking method, this paper designed and realized a simple and effective object tracking method. At first, proposed a pixel intensity classification and the single Gaussian model based background reconstruction algorithm. Then use the background subtraction method to extract the foreground target as the initialization of the tracking algorithm. Finally, apply the Kalman filter based camshift algorithm to track the moving target, which combined with a simple algorithm to solve the shadow problem, narrowing the search range of the target to achieve fast and real-time tracking, and making the tracking result more accurate.
Keywords :
Gaussian processes; Kalman filters; feature extraction; image classification; image reconstruction; object tracking; target tracking; Kalman filter-based camshift algorithm; adaptive background subtraction; background reconstruction algorithm; digital image processing; foreground target extraction; improved camshift algorithm; moving target tracking method; object tracking; pixel intensity classification; real-time tracking; single Gaussian model; tracking algorithm; Classification algorithms; Gray-scale; Image color analysis; Image reconstruction; Kalman filters; Prediction algorithms; Target tracking;
Conference_Titel :
Audio, Language and Image Processing (ICALIP), 2012 International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4673-0173-2
DOI :
10.1109/ICALIP.2012.6376745