Paper Infomation
Research on Anti-UAV Visual Detection Method Based on Deep Learning
Full Text(PDF, 1548KB)
Author: Yinggang Liang, Shaobo Wu
Abstract: The illegal intrusion of drones poses a significant threat to daily life and societal security. Existing methods that rely on microwave radar and machine learning are not effective in detecting low, slow, and small drone targets. For this reason, this paper proposes a deep learning-based anti-drone visual detection method. The DETR model is employed to identify high-altitude multi-scene drone targets. Specifically, a deformable attention module is introduced into the DETR model to enhance the detection accuracy of small target drones. To reduce the model's parameter count while maintaining detection accuracy and fulfilling the real-time requirements for unmanned aerial vehicles, the ShuffleNet V2 model is utilized to optimize the DETR backbone network. Furthermore, a mixed attention mechanism is incorporated. Experimental results demonstrate that the improved model achieves an average accuracy increase of 2.4% compared to the original DETR model (mAP@0.5), with a 5.9% enhancement in small target detection accuracy. The lightweight improvements made to the model backbone network reduce the parameter count from 66.5Mb to 43.8Mb, resulting in improved detection speed and meeting the real-time and deployment requirements of the drone detection model.
Keywords: Anti-UAV, Deep Learning, Target Detection, DETR, Lightweight
References:
[1] Fan Z, Gao X, Jin Y, et al. Research on Route Planning of Group UAV Cooperation for Deception Jamming to Radar Network[C]// IEEE Information Technology, Networking, Electronic and Automation Control Conference. IEEE, 2020.
[2] Jiang C, Fang Y, Zhao P, et al. Intelligent UAV Identity Authentication and Safety Supervision based on Behavior Modeling and Prediction[J]. IEEE Transactions on Industrial Informatics, 2020, PP (99):1-1.
[3] Viola P, Jones M J. Robust real-time face detection[J]. International journal of computer vision, 2004, 57: 137-154.
[4] Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]//2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05). Ieee, 2005, 1: 886-893
[5] Felzenszwalb P F, Girshick R B, McAllester D, et al. Object detection with discriminatively trained part-based models[J]. IEEE transactions on pattern analysis and machine intelligence, 2009, 32(9): 1627-1645.
[6] Nalamati M, Kapoor A, Saqib M, et al. Drone detection in long-range surveillance videos[C]//2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE, 2019: 1-6.
[7] Garcia A J, Lee J M, Kim D S. Anti-drone system: A visual-based drone detection using neural networks[C]//2020 International Conference on Information and Communication Technology Convergence (ICTC). IEEE, 2020: 559-561.
[8] Xun D T W, Lim Y L, Srigrarom S. Drone detection using YOLOv3 with transfer learning on NVIDIA Jetson TX2[C]//2021 Second International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics (ICA-SYMP). IEEE, 2021: 1-6.
[9] 薛珊,张亚亮,吕琼莹等.复杂背景下的反无人机系统目标检测算法[J].吉林大学学报(工学版), 2023,53(03):891-901.DOI:10.13229/j.cnki.jdxbgxb.20221288.
[10] Carion N, Massa F, Synnaeve G, et al. End-to-end object detection with transformers[C]//European conference on computer vision. Cham: Springer International Publishing, 2020: 213-229.
[11] Zhu X. Su W, Lu L, et al. Deformable detr: Deformable transformers for end-to-end object detection[J]. arXiv preprintarXiv:2010.04159.2020
[12] Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 2117-2125.
[13] Ma N, Zhang X, Zheng H T, et al. Shufflenet v2: Practical guidelines for efficient cnn architecture design[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 116-131.
[14] Woo S, Park J, Lee J Y, et al. Cbam: Convolutional block attention module[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 3-19.
[15] Zhao J, Zhang J, Li D, et al. Vision-based anti-uav detection and tracking[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(12): 25323-25334.