ML Anthology

CenterNet Heatmap Propagation for Real-Time Video Object Detection

Zhujun Xu, Emir Hrustic, Damien Vivet
ECCV 2020
doi:10.1007/978-3-030-58595-2_14 /eccv/2020/xu2020eccv-centernet/

Abstract

The existing methods for video object detection mainly depend on two-stage image object detectors. The fact that two-stage detectors are generally slow makes it difficult to apply in real-time scenarios. Moreover, adapting directly existing methods to a one-stage detector is inefficient or infeasible. In this work, we introduce a method based on a one-stage detector called CenterNet. We propagate the previous reliable long-term detection in the form of heatmap to boost results of upcoming image. Our method achieves the online real-time performance on ImageNet VID dataset with 76.7% mAP at 37 FPS and the offline performance 78.4% mAP at 34 FPS.

PDF ECCV Semantic Scholar

Cite

Text

Xu et al. "CenterNet Heatmap Propagation for Real-Time Video Object Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58595-2_14

Markdown

[Xu et al. "CenterNet Heatmap Propagation for Real-Time Video Object Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/xu2020eccv-centernet/) doi:10.1007/978-3-030-58595-2_14

BibTeX

@inproceedings{xu2020eccv-centernet,
  title     = {{CenterNet Heatmap Propagation for Real-Time Video Object Detection}},
  author    = {Xu, Zhujun and Hrustic, Emir and Vivet, Damien},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58595-2_14},
  url       = {https://mlanthology.org/eccv/2020/xu2020eccv-centernet/}
}