RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images

Abstract

Recent methods for people detection in overhead, fisheye images either use radially-aligned bounding boxes to represent people, assuming people always appear along image radius or require significant pre-/post-processing which radically increases computational complexity. In this work, we develop an end-to-end rotation-aware people detection method, named RAPiD, that detects people using arbitrarily-oriented bounding boxes. Our fully-convolutional neural network directly regresses the angle of each bounding box using a periodic loss function, which accounts for angle periodicities. We have also created a new dataset1 with spatio-temporal annotations of rotated bounding boxes, for people detection as well as other vision tasks in overhead fisheye videos. We show that our simple, yet effective method outperforms state-of-the-art results on three fisheye-image datasets. The source code for RAPiD is publicly available2.

Cite

Text

Duan et al. "RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00326

Markdown

[Duan et al. "RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/duan2020cvprw-rapid/) doi:10.1109/CVPRW50498.2020.00326

BibTeX

@inproceedings{duan2020cvprw-rapid,
  title     = {{RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images}},
  author    = {Duan, Zhihao and Tezcan, Mustafa Ozan and Nakamura, Hayato and Ishwar, Prakash and Konrad, Janusz},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2020},
  pages     = {2700-2709},
  doi       = {10.1109/CVPRW50498.2020.00326},
  url       = {https://mlanthology.org/cvprw/2020/duan2020cvprw-rapid/}
}