Corpus ID: 211858543

Rethinking Temporal Object Detection from Robotic Perspectives

@inproceedings{Chen2019RethinkingTO,
  title={Rethinking Temporal Object Detection from Robotic Perspectives},
  author={Xingyu Chen and Zhengxing Wu and Junzhi Yu and Li Wen},
  year={2019}
}
  • Xingyu Chen, Zhengxing Wu, +1 author Li Wen
  • Published 2019
  • Video object detection (VID) has been vigorously studied for years but almost all literature adopts a static accuracy-based evaluation, i.e., average precision (AP). From a robotic perspective, the importance of recall continuity and localization stability is equal to that of accuracy, but the AP is insufficient to reflect detectors' performance across time. In this paper, non-reference assessments are proposed for continuity and stability based on object tracklets. These temporal evaluations… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.

    On the stability of video detection and tracking

    • H. Zhang, N. Wang
    • arXiv:1611.06467, 2016.
    • 2016
    VIEW 2 EXCERPTS