城市低空小型无人机目标实时高精度检测算法

doi:10.3778/j.issn.1002-8331.2305-0319

摘要/Abstract

摘要： 面向城市低空小型无人机（unmanned aerial vehicle，UAV）乱飞引发的公共安全隐患，针对目前存在的动小目标检测精度低、实时性差等问题，提出了一种基于改进YOLOv7的目标检测模型。该模型在主干网络中引入RepVGG轻量化网络，降低计算复杂度以满足实时性要求；提出C3m模块以解决无人机小目标在图像中占比小、特征信息有限等问题，从而改善检测精度；在此基础上，将CBAM卷积注意力机制插入到主干网络和特征融合网络之间，提高网络对多尺度无人机目标的敏感度，降低噪声影响。在自构建的城市低空无人机数据集上进行消融实验，结果表明改进后的YOLOv7模型与原始YOLOv7模型相比，参数量减少了6×106，浮点运算量降低了77.9%，检测精度mAP@0.5提高至95.1%，检测速度FPS提高了43.7%，实现了对复杂场景下小型无人机目标的实时高精度检测。

关键词: YOLOv7, 无人机检测, 轻量化网络, 注意力机制

Abstract: In response to the public safety hazards caused by small UAVs (unmanned aerial vehicles) flying indiscriminately at low altitude in cities, a target detection model based on improved YOLOv7 is proposed to address the existing problems of low accuracy and poor real-time detection of small moving targets. The RepVGG lightweight network is introduced into the backbone network to reduce computational complexity and achieve real-time detection requirements. Meanwhile, a C3m module is proposed to solve the issues of small UAV targets with limited presence and limited feature information in images, so as to improve the detection accuracy. On this basis, the CBAM convolutional attention mechanism is inserted between the backbone network and the feature fusion network to improve the sensitivity of the network to multi-scale UAV targets and reduce the influence of noise. Finally, extensive experiments are conducted on a self-built urban low-altitude UAV dataset. The results demonstrate that the improved YOLOv7 model, compared to the original YOLOv7 model, reduces the number of parameters by 6×106, decreases the floating-point operations by 77.9%, increases the detection accuracy (mAP@0.5) to 95.1%, improves the detection speed (FPS) by 43.7%, thus achieving real-time and high-precision detection of UAV.

Key words: YOLOv7, UAV detection, lightweight network, attention mechanism

崔勇强, 黄谦, 高雪, 梅涛, 白迪, 王晓磊. 城市低空小型无人机目标实时高精度检测算法[J]. 计算机工程与应用, 2024, 60(16): 198-205.

CUI Yongqiang, HUANG Qian, GAO Xue, MEI Tao, BAI Di, WANG Xiaolei. Real-Time High-Precision Detection Algorithm for Small UAV Targets in Urban Low-Altitude Areas[J]. Computer Engineering and Applications, 2024, 60(16): 198-205.

参考文献

[1] DIDKOVSKYI V, KOZERUK S, KORZHIK O. Simple acoustic array for small UAV detection[C]//Proceedings of the 2019 IEEE 39th International Conference on Electronics and Nanotechnology, 2019: 656-659.
[2] VAN NGUYEN H, REZATOFIGHI H, VO B N, et al. Online UAV path planning for joint detection and tracking of multiple radio-tagged objects[J]. IEEE Transactions on Signal Processing, 2019, 67(20): 5365-5379.
[3] AI X, ZHANG L, ZHENG Y, et al. Passive detection experiment of UAV based on 5G new radio signal[C]//Proceedings of the 2021 Photonics & Electromagnetics Research Symposium, 2021: 2124-2129.
[4] KAPOULAS I K, HATZIEFREMIDIS A, BALDOUKAS A K, et al. Small fixed-wing UAV radar cross-section signature investigation and detection and classification of distance estimation using realistic parameters of a commercial anti-drone system[J]. Drones, 2023, 7(1): 39.
[5] 罗俊海，王芝燕. 无人机探测与对抗技术发展及应用综述[J]. 控制与决策, 2022, 37(3): 530-544.
LUO J H, WANG Z Y. A review of development and application of UAV detection and counter technology[J]. Control and Decision, 2022, 37(3): 530-544.
[6] 张灵灵, 王鹏, 李晓艳, 等. 基于优化SSD的低空无人机检测方法[J]. 计算机工程与应用, 2022, 58(16): 204-212.
ZHANG L L, WANG P, LI X Y, et al. Low-altitude UAV detection method based on optimized SSD[J]. Computer Engineering and Applications, 2022, 58(16): 204-212.
[7] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision, Amsterdam, Oct 11-14, 2016. Cham: Springer, 2016: 21-37.
[8] HU Y, WU X, ZHENG G, et al. Object detection of UAV for anti-UAV based on improved YOLO v3[C]//Proceedings of the 2019 Chinese Control Conference, 2019: 8386-8390.
[9] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7263-7271.
[10] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[11] LV Y, AI Z, CHEN M, et al. High-resolution drone detection based on background difference and SAG?YOLOv5s[J]. Sensors, 2022, 22(15): 5825.
[12] ROZANTSEV A, LEPETIT V, FUA P. Detecting flying objects using a single moving camera[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(5): 879-892.
[13] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[J]. arXiv:2207.02696, 2022.
[14] 王琳毅, 白静, 李文静, 等. YOLO系列目标检测算法研究进展[J]. 计算机工程与应用, 2023, 59(14):15-29.
WANG L Y, BAI J, LI W J, et al. Research progress of YOLO series target detection algorithms[J]. Computer Engineering and Applications, 2023, 59(14): 15-29.
[15] DING X, ZHANG X, MA N, et al. RepVGG: making VGG-style ConvNets great again[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2021: 13733-13742.
[16] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv:1409. 1556, 2014.
[17] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the 15th European Conference on Computer Vision, 2018: 3-19.
[18] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems 28, 2015.
[19] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[20] GE Z, LIU S, WANG F, et al. YOLOx: exceeding YOLO series in 2021[J]. arXiv:2107.08430, 2021.
[21] ZHU X, LYU S, WANG X, et al. TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021: 2778-2788.