Abstract | ||
---|---|---|
Pedestrian tracking has been a popular research topic and application in the field of computer vision. Recently group information has been receiving increasing attention for pedestrian tracking, especially in highly occluded scenarios that make traditional vision features unreliable. In this paper, we propose a novel multi-camera pedestrian tracking system which incorporates a pedestrian grouping strategy and an online cross-camera model. The new cross-camera model is able to take the advantage of the information from all camera views as well as the group structure in the inference stage, and can be updated based on the learning approach from structured SVM. The experimental results demonstrate the improvement in tracking performance when grouping stage is integrated. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1145/2659021.2659023 | ICDSC |
Keywords | Field | DocType |
group structure,algorithms,pedestrian tracking,tracking,multi-camera | Structured support vector machine,Computer vision,Pedestrian,Group structure,Multi camera,Inference,Computer science,Tracking system,Artificial intelligence | Conference |
Citations | PageRank | References |
1 | 0.35 | 18 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhixing Jin | 1 | 12 | 2.95 |
Bir Bhanu | 2 | 3356 | 380.19 |