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%. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/IIH-MSP.2009.239 | IIH-MSP |
Keywords | Field | DocType |
crowd scene,inaccurate foreground detection,tracked target,multi-mode multi-target tracking method,abovementioned problem,multi-mode multi-target tracking scheme,target detection,ground point detection,multi-mode tracking scheme,tracking efficiency,multiple target tracking,data mining,accuracy,pixel,head,image texture | Object detection,Computer vision,Multi target tracking,Pattern recognition,Image texture,Computer science,Foreground detection,Artificial intelligence,Pixel | Conference |
Citations | PageRank | References |
1 | 0.44 | 2 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Cheng-Chang Lien | 1 | 128 | 13.15 |
Ya-Lin Huang | 2 | 28 | 4.37 |
Chin-Chuan Han | 3 | 668 | 62.34 |