Multi-person Tracking by Online Learned Grouping Model with Non-linear Motion Context

@inproceedings{Chen2015MultipersonTB,
  title={Multi-person Tracking by Online Learned Grouping Model with Non-linear Motion Context},
  author={Xiaojing Chen and Zhen Qin and Bir Bhanu},
  year={2015}
}
An online approach to learn elementary groups containing only two targets, i.e., pedestrians, for inferring high level context is introduced to improve multi-person tracking. In most existing data association-based tracking approaches, only low level information (e.g., time, appearance, and motion) are used to build the affinity model, and each target is considered as an independent agent. Unlike those previous methods, in this paper, an online learned social grouping behavior model is used to… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 39 references

Pedestrian tracking with crowd simulation models in a multi-camera system,

  • Z. Jin, B. Bhanu
  • Computer Vision and Image Understanding,
  • 2014
1 Excerpt

Similar Papers

Loading similar papers…