logo

SCIENCE CHINA Information Sciences, Volume 63 , Issue 7 : 179203(2020) https://doi.org/10.1007/s11432-018-9633-7

Deep learning network for UAV person re-identification based on residual block

More info
  • ReceivedJun 21, 2018
  • AcceptedJul 4, 2018
  • PublishedFeb 27, 2020

Abstract

There is no abstract available for this article.


Supplement

Figure S1 aerial person images, Figure S2 network structure, and Figure S3 qualitative results.


References

[1] Peng K, Lin F, Chen B M. Online schedule for autonomy of multiple unmanned aerial vehicles. Sci China Inf Sci, 2017, 60: 072203 CrossRef Google Scholar

[2] Avola D, Foresti G L, Martinel N, et al. Aerial video surveillance system for small-scale UAV environment monitoring. In: Proceedings of IEEE International Conference on Advanced Video and Signal Based Surveillance, Lecce, 2017. Google Scholar

[3] Duan H, Li H, Luo Q. A binocular vision-based UAVs autonomous aerial refueling platform. Sci China Inf Sci, 2016, 59: 053201 CrossRef Google Scholar

[4] Roth P M, Wohlhart P, Hirzer M, et al. Large scale metric learning from equivalence constraints. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, 2012. 2288--2295. Google Scholar

[5] Schumann A, Schuchert T. Person re-identification in UAV videos using relevance feedback. The International Society for Optical Engineering, 2015, 9407: 8, doi: 10.1117/12.2083405. Google Scholar

[6] Zheng L, Shen L Y, Tian L, et al. Scalable person re-identification: a benchmark. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), Santiago, 2015. 1116--1124. Google Scholar

[7] Hirzer M, Roth P M, Bischof H. Person re-identification by efficient impostor-based metric learning. In: Proceedings of Advanced Video and Signal Based Surveillance (AVSS), Beijing, 2012. 203--208. Google Scholar

[8] Hadsell R, Chopra S. Dimensionality reduction by learning an invariant mapping. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, New York, 2006. 1735--1742. Google Scholar

[9] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. Google Scholar

  • Table 1   ResNet34 accuracy
    Dataset CMC rank 1 (%) CMC rank 5 (%) mAP (%)
    VIPeR 72.1 74.8 62.7
    Market1501 75.2 82.5 66.9
    CUHK03 79.3 85.3 69.9
    VIPeR[Ours] 71.9 73.9 62.1
    Market1501[Ours] 81.2 89.6 70.9
    CUHK03[Ours] 83.7 89.8 72.9

Copyright 2020  CHINA SCIENCE PUBLISHING & MEDIA LTD.  中国科技出版传媒股份有限公司  版权所有

京ICP备14028887号-23       京公网安备11010102003388号