Abstract | ||
---|---|---|
In this paper we present a novel and robust framework that decomposes continuous people detection into three parts, including off-line detection, tracking and learning. We introduce temporal coherence and spatial constraints into off-line detection phase by collecting a dynamical model from tracker which is estimated and updated by the learning algorithm. This method makes the detector aim at regions where a potential target will appear in the next frame, capable of handling pedestrians with occlusions and variety of scales, which as result greatly improves performance of pedestrian detection. We carry out a quantitative and qualitative evaluation on the public datasets. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/PDCAT.2012.110 | PDCAT |
Keywords | Field | DocType |
off-line detection,next frame,qualitative evaluation,pedestrian detection directing,public datasets,dynamical model,detector aim,pedestrian detection,continuous people detection,potential target,off-line detection phase,object tracking | Object detection,Computer vision,Viola–Jones object detection framework,Pattern recognition,Object-class detection,Corner detection,Computer science,Tracking system,Video tracking,Artificial intelligence,Detector,Pedestrian detection | Conference |
Citations | PageRank | References |
0 | 0.34 | 14 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hongmei Li | 1 | 0 | 0.34 |
Rentao Gu | 2 | 25 | 8.24 |
Qing Ye | 3 | 1 | 0.71 |
Yuefeng Ji | 4 | 303 | 49.02 |