改进YOLOv7的X光图像危险品检测算法

doi:10.3778/j.issn.1002-8331.2308-0444

摘要/Abstract

摘要： 针对X光安检图像在危险品检测时背景复杂、遮挡严重、尺度多变等问题，对YOLOv7算法进行了改进，在提高检测精度的同时使网络更加轻量化。首先构建PS-ELAN模块替换原主干网络中的ELAN模块，减少网络计算量和内存占用，同时提升网络的特征提取能力。其次将无参注意力机制SimAM与可变形卷积DCNv2融合至颈部网络的下采样阶段，提高网络对X光图像危险品关键特征的捕捉能力。最后引入Dynamic Head模块，增强检测头的尺度感知、空间感知和任务感知，提高网络的检测性能。实验结果表明，改进后的算法在自制数据集和CLCXray数据集上的平均精度均值（mean average precision，mAP）比原YOLOv7模型分别提高了4.7个百分点和1.2个百分点，参数量和计算量分别下降了16.2%和23.1%。改进后的算法提高了检测能力，同时更为轻量化，可在实际安检中起到很好的辅助作用。

关键词: 深度学习, X光安检图像, 危险品检测, YOLOv7, 注意力机制

Abstract: Aiming at the problems of complex background, serious occlusion and variable scale of X-ray security inspection images in dangerous goods detection, the YOLOv7 algorithm is improved, which improves the detection accuracy and makes the network more lightweight. Firstly, the PS-ELAN module is built to replace the ELAN module in the original backbone network, which reduces the network computing amount and memory occupation, and improves the feature extraction capability of the network. Secondly, the parameter-free attention mechanism SimAM and deformable convolutional DCNv2 are fused into the downsampling stage of the neck network to improve the network’s ability to capture the key features of dangerous goods in X-ray images. Finally, the Dynamic Head module is introduced to enhance the scale perception, spatial perception and task perception of the detection head, and improve the detection performance of the network. Experimental results show that the mean average precision (mAP) of the improved algorithm on the self-made dataset and CLCXray dataset is improved by 4.7 percentage points and 1.2 percentage points, respectively, and the number of parameters and calculations are reduced by 16.2% and 23.1%, respectively. The improved algorithm makes detection capability lighter, which can play a good role in actual security checks.

Key words: deep learning, X-ray security inspection image, dangerous goods, YOLOv7, attention mechanism

张继龙, 赵军, 李金龙. 改进YOLOv7的X光图像危险品检测算法[J]. 计算机工程与应用, 2024, 60(10): 266-275.

ZHANG Jilong, ZHAO Jun, LI Jinlong. Improved Dangerous Goods Detection in X-Ray Images of YOLOv7[J]. Computer Engineering and Applications, 2024, 60(10): 266-275.

参考文献

[1] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587.
[2] 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, 2017, 39(6): 1137-1149.
[3] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision. Cham: Springer, 2016: 21-37.
[4] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7263-7271.
[5] REDMON J, FARHADI A. Yolov3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[6] BOCHKOVSKIY A, WANG C Y, LIAO H. YOLOv4: optimal speed and accuracy of object detection[C]//Proceedings of the 2020 IEEE Conference on Computer Vision and Pattern Recognition, 2020.
[7] JOCHER G, CHAURASIA A, et al. YOLOv5[EB/OL]. [2023-06-08]. https://github.com/ultralytics/yolov5.
[8] 郭瑞鸿, 张莉, 杨莹, 等.基于改进SSD的X光图像管制刀具检测与识别[J].激光与光电子学进展, 2021, 58(4): 65-72.
GUO R H, ZHANG L, YANG Y, et al. X-ray image controlled knife detection and recognition based on improved SSD[J]. Laser & Optoelectronics Progress, 2021, 58(4): 65-72.
[9] 吴海滨, 魏喜盈, 刘美红, 等.结合空洞卷积和迁移学习改进YOLOv4的X光安检危险品检测[J].中国光学, 2021, 14(6): 1417-1425.
WU H B, WEI X Y, LIU M H, et al. Improved YOLOv4 for dangerous goods detection in X?ray inspection combined with atrous convolution and transfer learning[J]. Chinese Optics, 2021, 14(6): 1417-1425.
[10] 穆思奇, 林进健, 汪海泉, 等.基于改进YOLOv4的X射线图像违禁品检测算法[J].兵工学报, 2021, 42(12): 2675-2683.
MU S Q, LIN J J, WANG H Q, et al. An algorithm for detection of prohibited items in X-ray images based on im-proved YOLOv4[J]. Acta Armamentarii, 2021, 42(12): 2675-2683.
[11] 董乙杉, 李兆鑫, 郭靖圆, 等.一种改进YOLOv5的X光违禁品检测模型[J].激光与光电子学进展, 2023, 60(4): 359-366.
DONG Y S, LI Z X, GUO J Y, et al. Improved YOLOv5 model for X-ray prohibited item detection[J]. Laser & Optoelectronics Progress, 2023, 60(4): 359-366.
[12] 李文强, 陈莉, 谢旭, 等.改进YOLOv5的X光图像违禁品检测算法[J].计算机工程与应用, 2023, 59(16): 170-176.
LI W Q, CHEN L, XIE X, et al. Algorithm for detecting prohibited items in X-ray images based on improved YOLOv5[J]. Computer Engineering and Applications, 2023, 59(16): 170-176.
[13] 赵振兵, 王帆帆, 刘良帅, 等.基于注意力特征融合YOLOv5模型的无人机输电线路航拍图像金具检测方法[J].电测与仪表, 2023, 60(3): 145-152.
ZHAO Z B, WANG F F, LIU L S, et al. Hardware detection method of aerial image of UAV transmission line based on attention feature fusion YOLOv5 model[J]. Electrical Measurement & Instrumentation, 2023, 60(3): 145-152.
[14] 胡皓, 郭放, 刘钊.改进YOLOX-S模型的施工场景目标检测[J].计算机科学与探索, 2023, 17(5): 1089-1101.
HU H, GUO F, LIU Z. Object detection based on improved YOLOX-S model in construction sites[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(5): 1089-1101.
[15] 粟兴旺, 王晓明, 黄金玻, 等.基于可变形卷积与注意力机制的X光安检违禁品检测[J].电子测量技术, 2023, 46(10): 98-108.
SU X W, WANG X M, HUANG J B, et al. Prohibited itemsdetection based on deformable convolution and attention mechanism in X-ray security inspection[J]. Electronic Measurement Technology, 2023, 46(10): 98-108.
[16] 孙嘉傲, 董乙杉, 郭靖圆, 等. 自适应与多尺度特征融合的X光违禁品检测[J]. 计算机工程与应用, 2024, 60(2): 96-102.
SUN J A, DONG Y S, GUO J Y, et al. Detection of X-ray contraband by adaptive and multi-scale feature fusion[J]. Computer Engineering and Applications, 2024, 60(2): 96-102.
[17] 张良, 薛志诚.基于自适应多尺度特征融合的X光违禁品检测[J/OL].信号处理 [2023-09-09].https: //kns-cnki-net.webvpn.las.ac.cn/kcms/detail/11.2406.tn.20230831.1616.
004.html.
ZHANG L, XUE Z C. X-ray prohibited items detection based on adaptive multi-scale feature fusion[J/OL]. Journal of Signal Processing [2023-09-09]. https://kns-cnki-net.webvpn.las.ac.cn/kcms/detail/11.2406.tn.20230831.1616.004.html.
[18] 李松, 亚森江·木沙.改进YOLOv7的X射线图像违禁品实时检测[J]. 计算机工程与应用, 2023, 59(12): 193-200.
LI S, YASENJIANG M. Improved YOLOv7 X-ray image real-time detection of prohibited items[J]. Computer Engineering and Applications, 2023, 59(12): 193-200.
[19] 成浪, 敬超.基于改进YOLOv7的X线图像旋转目标检测[J]. 图学学报, 2023, 44(2): 324-334.
CHENG L, JING C. X-ray image rotating object detection based on improved YOLOv7[J]. Journal of Graphics, 2023, 44(2): 324-334.
[20] CHEN J, KAO S, HE H, et al. Run, don’t walk: chasing higher flops for faster neural networks[J]. arXiv:2303. 03667, 2023.
[21] ZHANG Q L, YANG Y B. SA-Net: shuffle attention for deep convolutional neural networks[C]//Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing, 2021: 2235-2239.
[22] YANG L, ZHANG Y, LI L, et al.SimAM: a simple, parameter-free attention module for convolutional neural networks[C]//Proceedings of the 38th International Conference on Machine Learning, 2021: 11863-11874.
[23] ZHU X Z, HU H, LIN S, et al. Deformable ConvNets v2: more deformable, better results[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 9308-9316.
[24] DAI X Y, CHEN Y P, XIAO B, et al. Dynamic head: unifying object detection heads with attentions[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 7369-7378.
[25] CHEN Y P, DAI X Y, LIU M C, et al. Dynamic ReLU[J]. arXiv:2003.10027, 2020.
[26] ZHAO C, ZHU L, DOU S, et al. Detecting overlapped objects in X-ray security imagery by a label-aware mechanism[J]. IEEE Transactions on Information Forensics and Security, 2022, 17: 998-1009.