高动态场景下无人机空对空目标检测

doi:10.19678/j.issn.1000-3428.0068620

摘要/Abstract

摘要：

针对高动态场景下无人机(UVA)空对空目标检测任务中机载设备计算资源有限和UVA小目标检测困难的问题, 提出一种基于轻量级注意力机制的无人机空对空目标检测算法SGC-YOLOv5。首先, 设计S-Ghost模块和SD-Ghost结构构建特征提取网络SD-GhostNet, 降低模型参数量和计算复杂度; 其次, 引入更高效的GSConv和VOVGSCSP结构细化特征融合网络, 将SD-GhostNet和细化的特征融合网络相结合使模型达到最佳的轻量化效果; 最后, 在特征融合网络中加入轻量级卷积块注意力模块(CBAM)来突出图像中感兴趣的UVA特征, 抑制背景冗余信息, 提高检测精度。在数据集Det-Fly上的实验结果表明, SGC-YOLOv5算法的精确率为74.9%、参数量为4 313 695、检测速度为169.42帧/s、每秒浮点运算次数(FLOPs)为9.0×10⁹, 与基准YOLOv5s算法相比, 检测精确率提升2.5%、参数量减少48.5%、检测速度提升26.17帧/s、FLOPs降低57.5%, 在实现模型轻量化的同时取得了较好的检测精确率。

关键词: 视觉目标检测, 无人机空对空目标检测, YOLOv5算法, 轻量化, 注意力机制

Abstract:

To address the issues of limited onboard computing resources and the difficulty of recognizing small targets in Unmanned Aerial Vehicle (UAV) air-to-air target detection tasks in high dynamic scenarios, a UAV air-to-air target detection algorithm based on a lightweight attention mechanism, SGC-YOLOv5, is proposed. First, the S-Ghost module and SD-Ghost structure are used to build an SD-GhostNet, a feature extraction network, which reduces the computational complexity and number of parameters of the model. Second, more efficient GSConv and VOVGSCSP structures are introduced to refine the feature fusion network, and SD-GhostNet is combined with the refined feature fusion network to achieve the best lightweight effect of the mode. Finally, a lightweight Convolutional Block Attention Module (CBAM) is added to the feature fusion network to highlight the UAV features of interest in the image, suppress redundant background information, and improve detection accuracy. Experimental results on the Det-Fly dataset indicate that the SGC-YOLOv5 algorithm achieves an accuracy, parameter count, detection speed, Floating Point Operations Per Second (FLOPs) of 74.9%, 4 313 695, 169.42 frames per second, and 9.0×10⁹, respectively. Compared with the benchmark YOLOv5s algorithm, the detection accuracy and detection speed are improved by 2.5% and 26.17 frames per second, respectively, whereas the parameter count and FLOPs are reduced by 48.5% and 57.5%, respectively. This model achieves good detection accuracy while achieving a lightweight model.

Key words: visual object detection, Unmanned Aerial Vehicle(UVA) air-to-air target detection, YOLOv5 algorithm, lightweight, attention mechanism

王林, 赵莉, 王无为. 高动态场景下无人机空对空目标检测[J]. 计算机工程, 2024, 50(12): 265-275.

WANG Lin, ZHAO Li, WANG Wuwei. Air-to-Air Target Detection of Unmanned Aerial Vehicles Under High Dynamic Scenarios[J]. Computer Engineering, 2024, 50(12): 265-275.

https://www.ecice06.com/CN/Y2024/V50/I12/265

图/表 13

图1 Ghost和GSConv模块

Fig.1 Ghost and GSConv module

图2 SGC-YOLOv5网络结构

Fig.2 SGC-YOLOv5 network structure

图3 S-Ghost和普通卷积模块

Fig.3 S-Ghost and ordinary convolution module

图4 SD-Ghost结构和信息增强过程

Fig.4 SD-Ghost structure and information enhancement process

图5 普通卷积与DWConv

Fig.5 Ordinary convolution and DWConv

图6 VOVGSCSP结构

Fig.6 VOVGSCSP structure

图7 CBAM结构

Fig.7 CBAM structure

图8 SGC-YOLOv5算法训练结果曲线

Fig.8 Training result curves of SGC-YOLOv5 algorithm

图9 多指标差异程度对比

Fig.9 Comparison of the degree of variation of multiple indicators

图10 不同背景下的UVA目标检测

Fig.10 UVA target detection under different backgrounds

参考文献 27

1	WAQAS S , MUBARAK S . Human action recognition in drone videos using a few aerial training examples. Computer Vision and Image Understanding, 2021, 206, 103186. doi: 10.1016/j.cviu.2021.103186
2	齐妙, 徐慧, 李森, 等. 一种基于双流网络的行为识别方法. 吉林大学学报(理学版), 2023, 61 (2): 347- 352. URL
	QI M , XU H , LI S , et al. An action recognition method based on two-stream network. Journal of Jilin University (Science Edition), 2023, 61 (2): 347- 352. URL
3	祖鑫萍, 李丹. 基于无人机图像和改进YOLOv3-SPP算法的森林火灾烟雾识别方法. 林业工程学报, 2022, 7 (5): 142- 149. URL
	ZU X P , LI D . Research on forest fire smoke identification method based on UAV images and improved YOLOv3-SPP algorithm. Journal of Forestry Engineering, 2022, 7 (5): 142- 149. URL
4	CAO Y R, HE Z J, WANG L J, et al. VisDrone-DET2021: the vision meets drone object detection challenge results[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Washington D.C., USA: IEEE Press, 2021: 2847-2854.
5	ROZANTSEV A , LEPETIT V , FUA P . Detecting flying objects using a single moving camera. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (5): 879- 892. doi: 10.1109/TPAMI.2016.2564408
6	HASSIJA V , CHAMOLA V , AGRAWAL A , et al. Fast, reliable, and secure drone communication: a comprehensive survey. IEEE Communications Surveys [WT《Times New Roman》]& Tutorials, 2021, 23 (4): 2802- 2832. doi: 10.1109/COMST.2021.3097916
7	GARCIA A J, LEE J M, KIM D S. Anti-drone system: a visual-based drone detection using neural networks[C]//Proceedings of the International Conference on Information and Communication Technology Convergence (ICTC). Washington D.C., USA: IEEE Press, 2020: 559-561.
8	REN S Q , HE K M , GIRSHICK R , et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
9	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2016: 770-778.
10	XUN D T W, LIM Y L, SRIGRAROM S. Drone detection using YOLOv3 with transfer learning on NVIDIA Jetson TX2[C]//Proceedings of the 2nd International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics (ICA-SYMP). Washington D.C., USA: IEEE Press, 2021: 1-6.
11	REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. [2023-09-04]. https://arxiv.org/abs/1804.02767.
12	DELLEJI T, FEKIH H, CHTOUROU Z. Deep Learning-based approach for detection and classification of micro/mini drones[C]//Proceedings of the 4th International Conference on Advanced Systems and Emergent Technologies (IC_ASET). Washington D.C., USA: IEEE Press, 2020: 332-337.
13	YAO J H , LI J F . AYOLOv3-Tiny: an improved convolutional neural network architecture for real-time defect detection of PAD light guide plates. Computers in Industry, 2022, 136, 103588. doi: 10.1016/j.compind.2021.103588
14	包文歧, 谢立强, 徐才华, 等. 基于YOLOv5的微小型无人机实时探测方法. 兵器装备工程学报, 2022, 43 (5): 232- 237. URL
	BAO W Q , XIE L Q , XU C H , et al. Real-time detection method of micro UAV based on YOLOv5. Journal of Ordnance Equipment Engineering, 2022, 43 (5): 232- 237. URL
15	彭晏飞, 赵涛, 陈炎康, 等. 基于上下文信息与特征细化的无人机小目标检测算法. 计算机工程与应用, 2024, 60 (5): 183- 190. doi: 10.3778/j.issn.1002-8331.2305-0401
	PENG Y F , ZHAO T , CHENG Y K , et al. UAV small object detection algorithm based on context information and feature refinement. Computer Engineering and Applications, 2024, 60 (5): 183- 190. doi: 10.3778/j.issn.1002-8331.2305-0401
16	LÜ Y W , AI Z Q , CHEN M F , et al. High-resolution drone detection based on background difference and SAG-YOLOv5s. Sensors, 2022, 22 (15): 5825. doi: 10.3390/s22155825
17	HAN K, WANG Y H, TIAN Q, et al. GhostNet: more features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2020: 1577-1586.
18	LI H L, LI J, WEI H B, et al. Slim-neck by GSConv: a better design paradigm of detector architectures for autonomous vehicles[EB/OL]. [2023-09-04]. http://arxiv.org/abs/2206.02424.
19	LIANG Y , LI M Z , JIANG C J , et al. CEModule: a computation efficient module for lightweight convolutional neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34 (9): 6069- 6080. doi: 10.1109/TNNLS.2021.3133127
20	王朕, 李豪, 严冬梅, 等. 基于改进YOLOv5的路面病害检测模型. 计算机工程, 2023, 49 (2): 15- 23. doi: 10.19678/j.issn.1000-3428.0064924
	WANG Z , LI H , YAN D M , et al. Pavement disease detection model based on improved YOLOv5. Computer Engineering, 2023, 49 (2): 15- 23. doi: 10.19678/j.issn.1000-3428.0064924
21	宋华伟, 屈晓娟, 杨欣, 等. 基于改进YOLOv5的火焰烟雾检测. 计算机工程, 2023, 49 (6): 250- 256. doi: 10.19678/j.issn.1000-3428.0064509
	SONG H W , QU X J , YANG X , et al. Flame and smoke detection based on improved YOLOv5. Computer Engineering, 2023, 49 (6): 250- 256. doi: 10.19678/j.issn.1000-3428.0064509
22	李嘉新, 侯进, 盛博莹, 等. 基于改进YOLOv5的遥感小目标检测网络. 计算机工程, 2023, 49 (9): 256- 264. doi: 10.19678/j.issn.1000-3428.0065935
	LI J X , HOU J , SHENG B Y , et al. Remote sensing small object detection network based on improved YOLOv5. Computer Engineering, 2023, 49 (9): 256- 264. doi: 10.19678/j.issn.1000-3428.0065935
23	WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV). Berlin, Germany: Springer, 2018: 3-19.
24	ZHENG Y , CHEN Z , LV D L , et al. Air-to-air visual detection of micro-UAVs: an experimental evaluation of deep learning. IEEE Robotics and Automation Letters, 2021, 6 (2): 1020- 1027. doi: 10.1109/LRA.2021.3056059
25	TANG Y H, HAN K, GUO J Y, et al. GhostNetV2: enhance cheap operation with long-range attention[EB/OL]. [2023-09-04]. http://arxiv.org/abs/2211.12905.
26	LIU Y C, SHAO Z R, HOFFMANN N. Global attention mechanism: retain information to enhance channel-spatial interactions[EB/OL]. [2023-09-04]. http://arxiv.org/abs/2112.05561.
27	YANG L X, ZHANG R R, LI L D, et al. SimAM: a simple, parameter-free attention module for convolutional neural networks[C]//Proceedings of International Conference on Machine Learning. New York, USA: PMLR Press, 2021: 11863-11874.

[1]	李俊俊, 董建刚, 李坤. 基于Kubernetes的集群节能策略研究[J]. 计算机工程, 2024, 50(9): 82-91.
[2]	林畅, 郭伟, 任哲聪, 金海波. 基于Transformer的目标跟踪与分割统一算法[J]. 计算机工程, 2024, 50(9): 130-141.
[3]	李泽霖, 吕兆峰, 陈富强, 李克. 基于多跳信息融合的实体对齐模型[J]. 计算机工程, 2024, 50(9): 142-152.
[4]	王汝英, 马嘉骏, 董建强, 刘万龙, 张海涛, 尹凯, 赵博超. 基于MTS-BiGRU-DMHSA的工业负荷预测方法[J]. 计算机工程, 2024, 50(9): 169-178.
[5]	朱凯, 李理, 张彤, 江晟, 别一鸣. 基于Transformer的多阶段运动模糊图像修复网络[J]. 计算机工程, 2024, 50(9): 276-285.
[6]	张天鹏, 韩晶, 吕学强. 基于多任务学习的超分辨率辅助小目标检测[J]. 计算机工程, 2024, 50(9): 304-312.
[7]	郭敏, 张熙涵, 李阳. 融合注意力的教师互一致性半监督医学图像分割[J]. 计算机工程, 2024, 50(9): 313-323.
[8]	曾钰琦, 刘博, 钟柏昌, 钟瑾. 智慧教育下基于改进YOLOv8的学生课堂行为检测算法[J]. 计算机工程, 2024, 50(9): 344-355.
[9]	饶日昕, 王怡文, 曾砺志, 童心恬, 赵海涛. 面向废旧电缆检测的轻量化网络模型[J]. 计算机工程, 2024, 50(8): 22-30.
[10]	李华昱, 张智康, 闫阳, 岳阳. 基于知识图谱增强的领域多模态实体识别[J]. 计算机工程, 2024, 50(8): 31-39.
[11]	王蕾, 党时鹏, 潘丰. 基于卷积神经网络的隐匿性旁路预测模型[J]. 计算机工程, 2024, 50(8): 40-49.
[12]	陈瀚, 赵春蕾, 蒋昊达, 王春东. 基于融合模型与语义网络的App用户意图识别研究[J]. 计算机工程, 2024, 50(8): 50-63.
[13]	王夙喆, 张雪英, 陈晓玉, 李凤莲, 吴泽林. 基于有效注意力和GAN结合的脑卒中EEG增强算法[J]. 计算机工程, 2024, 50(8): 336-344.
[14]	王宇, 祁琦, 王纯, 许才. 储能变流器信号高精度故障诊断方法[J]. 计算机工程, 2024, 50(8): 389-396.
[15]	王炼红, 林飞鹏, 李潇瑶, 谌桂枝, 周莉. 融入课程知识图谱的KMAKT预测[J]. 计算机工程, 2024, 50(7): 23-31.

选择文件类型/文献管理软件名称

选择包含的内容