Optimized Pedestrian Detection for Multiple and Occluded People

Sitapa Rujikietgumjorn, Robert T. Collins

CVPR 2013

doi:10.1109/CVPR.2013.473 /cvpr/2013/rujikietgumjorn2013cvpr-optimized/

Abstract

We present a quadratic unconstrained binary optimization (QUBO) framework for reasoning about multiple object detections with spatial overlaps. The method maximizes an objective function composed of unary detection confidence scores and pairwise overlap constraints to determine which overlapping detections should be suppressed, and which should be kept. The framework is flexible enough to handle the problem of detecting objects as a shape covering of a foreground mask, and to handle the problem of filtering confidence weighted detections produced by a traditional sliding window object detector. In our experiments, we show that our method outperforms two existing state-ofthe-art pedestrian detectors.

PDF CVPR Semantic Scholar

Cite

Text

Rujikietgumjorn and Collins. "Optimized Pedestrian Detection for Multiple and Occluded People." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.473

Markdown

[Rujikietgumjorn and Collins. "Optimized Pedestrian Detection for Multiple and Occluded People." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/rujikietgumjorn2013cvpr-optimized/) doi:10.1109/CVPR.2013.473

BibTeX

@inproceedings{rujikietgumjorn2013cvpr-optimized,
  title     = {{Optimized Pedestrian Detection for Multiple and Occluded People}},
  author    = {Rujikietgumjorn, Sitapa and Collins, Robert T.},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.473},
  url       = {https://mlanthology.org/cvpr/2013/rujikietgumjorn2013cvpr-optimized/}
}