Low-altitude UAV detection method based on optimized CenterNet

被引：0
|
作者：
Zhang R. [1 ]
Li N. [1 ,2 ]
Zhang X. [1 ]
Zhou H. [3 ]
机构：
[1] College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing
[2] Science and Technology on Electro-optic Control Laboratory, Luoyang
[3] University of Leicester, Leicester
来源：
Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics | 2022年 / 48卷 / 11期
关键词：
CenterNet; deep learning; joint attention; object detection; unmanned aerial vehicle;
D O I：
10.13700/j.bh.1001-5965.2021.0108
中图分类号：
学科分类号：
摘要：
To achieve effective detection of “low, slow and small” unmanned aerial vehicle(UAV) and improve detection accuracy and positioning quality, we propose a low-altitude UAV detection method based on joint attention and CenterNet. Aiming at the problem of high miss-detection rate of small targets in general target detection algorithms, a decoupled non-local operator is introduced to capture the relevance of target regions in optical images. Utilizing the similarity between individuals of the UAV group, the discrete UAV features are correlated to each other to reduce the missed detection rate. Moreover, to obtain more accurate detection boxes, we optimized the label coding strategy and bounding box regression method of CenterNet, and the positioning quality loss is introduced to improve the positioning quality of the detection boxes. Experimental results show that the optimized S-CenterNet algorithm has an average accuracy increase of 8. 9% compared with the original CenterNet, and the detection boxer positioning quality has been significantly improved. © 2022 Beijing University of Aeronautics and Astronautics (BUAA). All rights reserved.
引用
收藏
页码：2335 / 2344
页数：9
相关论文
共 19 条
  • [1] YU F, LIU D H, HE F Y., UAV “black flying” challenges the safety of electromagnetic space, China Radio, 8, pp. 43-44, (2018)
  • [2] GIRSHICK R, DONAHUE J, DARRELL T, Et al., Rich feature hierarchies for accurate object detection and semantic segmentation[C], Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, (2014)
  • [3] GIRSHICK R., Fast-RCNN, Proceedings of the IEEE Conference on Computer Vision, pp. 1440-1448, (2015)
  • [4] REN S, HE K, GIRSHICK R, Et al., Faster R-CNN: Towards real-time object detection with region proposal networks [J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 6, pp. 1137-1149, (2017)
  • [5] CAI Z, VASCONCELOS N., Cascade R-CNN: Delving into high quality object detection[C], Proceedings of 2018 IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154-6162, (2018)
  • [6] HE K, GKIOXARI G, DOLLAR P, Et al., Mask R-CNN[C], Proceedings of 2017 IEEE International Conference on Computer Vision, pp. 2980-2988, (2017)
  • [7] REDMON J, FARHADI A., YOLOv3: An incremental improvement
  • [8] LIN T, GOYAL P, GIRSHICK R, Et al., Focal loss for dense object detection, Proceedings of 2017 IEEE International Conference on Computer Vision, pp. 2999-3007, (2017)
  • [9] LAW H, DENG J., CornerNet: Detecting objects as paired key-points [J], International Journal of Computer Vision, 128, pp. 642-656, (2018)
  • [10] ZHOU X, WANG D, KRAHENBUHL P., Objects as points
12