Abstract | ||
---|---|---|
In this paper we introduce a novel surveillance system, which uses 3D information extracted from multiple cameras to detect, track and re-identify people. The detection method is based on a 3D Marked Point Process model using two pixel-level features extracted from multi-plane projections of binary foreground masks, and uses a stochastic optimization framework to estimate the position and the height of each person. We apply a rule based Kalman-filter tracking on the detection results to find the object-to-object correspondence between consecutive time steps. Finally, a 3D body model based long-term tracking module connects broken tracks and is also used to re-identify people. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICCVW.2011.6130469 | 2011 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCV WORKSHOPS) |
Keywords | Field | DocType |
kalman filters,image recognition,stochastic processes,data model,feature extraction,data models,solid modeling,three dimensional,rule based,information extraction,stochastic optimization,trajectory,reliability,kalman filter,object tracking | Computer vision,Data modeling,Object detection,Rule-based system,Stochastic optimization,Pattern recognition,Computer science,Kalman filter,Feature extraction,Video tracking,Artificial intelligence,Solid modeling | Conference |
Volume | Issue | Citations |
2011 | 1 | 13 |
PageRank | References | Authors |
0.66 | 16 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Davide Baltieri | 1 | 351 | 12.13 |
R. Vezzani | 2 | 847 | 53.39 |
Rita Cucchiara | 3 | 4174 | 300.55 |
Ákos Utasi | 4 | 49 | 6.40 |
Csaba Benedek | 5 | 193 | 21.31 |
Tamás Szirányi | 6 | 152 | 26.92 |