DocumentCode :
2464289
Title :
People Counting Using Multi-Mode Multi-Target Tracking Scheme
Author :
Lien, Cheng-Chang ; Huang, Ya-Lin ; Han, Chin-Chuan
Author_Institution :
Dept. of CSIE, Chung Hua Univ., Hsinchu, Taiwan
fYear :
2009
fDate :
12-14 Sept. 2009
Firstpage :
1018
Lastpage :
1021
Abstract :
Conventional video surveillance systems often have several shortcomings. First, target detection can´t be accurate under the light variation environment. Second, multiple target tracking becomes difficult on a crowd scene. Third, it is difficult to the partition the tracked targets from a merged image blob. Finally, the tracking efficiency and precision are reduced by the inaccurate foreground detection. In this paper, the fusion of temporal and texture background model, multi-mode tracking scheme, color-based difference projection, and ground point detection are proposed to improve the abovementioned problems. In addition, we propose a people counting scheme based on the multi-mode multi-target tracking method on a crowd scene. Experimental results show that the targets on the scene may be detected robustly with the rate above 10 fps and counted with the accuracy above 90%.
Keywords :
image colour analysis; image texture; object detection; target tracking; video surveillance; color-based difference projection; foreground detection; ground point detection; multimode multitarget tracking scheme; people counting; temporal background model; texture background model; video surveillance systems; Head; Histograms; Layout; Multimedia systems; Object detection; Robustness; Signal processing algorithms; Target tracking; Video signal processing; Video surveillance; Multi-mode multi-target tracking; People counting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Information Hiding and Multimedia Signal Processing, 2009. IIH-MSP '09. Fifth International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4244-4717-6
Electronic_ISBN :
978-0-7695-3762-7
Type :
conf
DOI :
10.1109/IIH-MSP.2009.239
Filename :
5337461
Link To Document :
بازگشت