Abstract | ||
---|---|---|
A novel pedestrian tracking scheme based on a particle filter is proposed, which adopts a skeleton model of a pedestrian as a state space model and uses distance transformed images for likelihood estimation. The six-stick skeleton model used in the proposed approach is very distinctive in representing a pedestrian simply but effectively, with which the efficient state space for the pedestrian tracking can be derived. Exper- imental results by using PETS sample sequences demonstrate that the proposed approach achieves highly accurate pedes- trian tracking without any of prior learning. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/ICIP.2006.312996 | ICIP |
Keywords | Field | DocType |
automotive engineering,image representation,image sequences,image thinning,maximum likelihood estimation,object detection,particle filtering (numerical methods),state-space methods,tracking filters,PETS sample sequences,distance transformed images,likelihood estimation,particle filter,probabilistic pedestrian tracking,six-stick skeleton model,state space model,Bayes procedures,Image processing,Tracking | Computer vision,Object detection,Pedestrian,Pattern recognition,Computer science,State-space representation,Particle filter,Image processing,Artificial intelligence,Probabilistic logic,Skeleton (computer programming),State space | Conference |
ISSN | Citations | PageRank |
1522-4880 | 2 | 0.44 |
References | Authors | |
5 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jumpei Ashida | 1 | 3 | 0.81 |
Ryusuke Miyamoto | 2 | 163 | 15.01 |
Hiroshi Tsutsui | 3 | 29 | 24.01 |
Takao Onoye | 4 | 329 | 68.21 |
Yukihiro Nakamura | 5 | 177 | 50.18 |