Improved YOLOv7 X-Ray Image Real-Time Detection of Prohibited Items

doi:10.3778/j.issn.1002-8331.2301-0158

Abstract

Abstract: The X-ray detection of prohibited items at the traffic entrance is very important for public safety. In order to achieve the detection accuracy and speed balance of prohibited items, the YOLOv7 algorithm is improved. A detector head generated from low-level and high-resolution feature map is added to improve the sensitivity to small target objects. MobileNetViTv3 block is added at the end of the Backone of YOLOv7 to capture global infomation and help the network accurately locate in high-density scenarios. An MPCA module is designed to compensate for the lack of deep convolution location information. Some advanced stragies are adopted to improve the effect of the model, such as data enhancement and additional clasfiers. The improved model is tested in three data sets of security prohibited items, SiXary, HiXary and CLCXray, and the mAP reaches 94.9%, 77.3% and 86.1% respectively. The results show that the proposed model can effectively improve the ability of YOLOv7 to detect complex prohibited items while maintaining a fast detection speed. Compared with the current mainstream algorithm, it has a certain degree of progressiveness.

Key words: X-ray image, prohibited items detection, attention mechanism, additional classifier

摘要： 交通入口处X光违禁品检测对公共安全至关重要，为了达到违禁品检测精度和速度均衡，对YOLOv7算法进行改进。增加了一个由低层、高分辨率的特征图生成的检测头，提高对小目标物体敏感度。在YOLOv7的Backbone末尾增加轻量级MobileNetViTv3 block，用于捕获全局信息，帮助网络在高密度场景中精准定位。并设计出一种MPCA模块用于弥补深层卷积定位信息的不足。在测试阶段引入一个额外的分类器，进一步提高网络的分类能力。改进后的模型在3种安检违禁品数据集SiXary、HiXary、CLCXray进行测试，mAP分别达到了94.9%、77.3%、86.1%。结果表明，所提出的模型能够有效提高YOLOv7的检测复杂违禁品的能力，同时保持较快的检测速度，与当前主流算法相比，具有一定的先进性。

关键词: X射线图像, 违禁品检测, 注意力机制, 额外分类器

LI Song, Yasenjiang Musa. Improved YOLOv7 X-Ray Image Real-Time Detection of Prohibited Items[J]. Computer Engineering and Applications, 2023, 59(12): 193-200.

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.

References

[1] 赵元龙，单玉刚，袁杰.改进YOLOv7与DeepSORT的佩戴口罩行人跟踪[J].计算机工程与应用，2023，59（6）：221-230.
ZHAO Y L，SHAN Y G，YUAN J.Wearing mask pedestrian tracking based on improved YOLOv7 and DeepSORT[J].Computer Engineering and Applications，2023，59（6）：221-230.
[2] 巢渊，刘文汇，唐寒冰，等.基于改进YOLO-v4的室内人脸快速检测方法[J].计算机工程与应用，2022，58（14）：105-113.
CHAO Y，LIU W H，TANG H B，et al.Fast indoor face detection method based on improved YOLO-v4[J].Computer Engineering and Applications，2022，58（14）：105-113.
[3] 王兵，李文璟，唐欢.改进YOLO v3算法及其在安全帽检测中的应用[J].计算机工程与应用，2020，56（9）：33-40.
WANG B，LI W J，TANG H.Improved YOLO v3 algorithm and its application in helmet detection[J].Computer Engineering and Applications，2020，56（9）：33-40.
[4] 钱伍，王国中，李国平.改进YOLOv5的交通灯实时检测鲁棒算法[J].计算机科学与探索，2022，16（1）：231-241.
QIAN W，WANG G Z，LI G P.Improved YOLOv5 traffic light real-time detection robust algorithm[J].Journal of Frontiers of Computer Science and Technology，2022，16（1）：231-241.
[5] 宋艳艳，谭励，马子豪，等.改进YOLOV3算法的视频目标检测[J].计算机科学与探索，2021，15（1）：163-172.
SONG Y Y，TAN L，MA Z H，et al.Video target detection based on improved YOLOV3 algorithm[J].Journal of Frontiers of Computer Science and Technology，2021，15（1）：163-172.
[6] 邵延华，张铎，楚红雨，等.基于深度学习的YOLO目标检测综述[J].电子与信息学报，2022，44（10）：3697-3708.
SHAO Y H，ZHANG D，CHU H Y，et al.A review of YOLO object detection based on deep learning[J].Journal of Electronics & Information Technology，2022，44（10）：3697-3708.
[7] LIN T Y，MAIRE M，BELONGIE S，et al.Microsoft coco：common objects in context[C]//European Conference on Computer Vision.Cham：Springer，2014：740-755.
[8] EVERINGHAM M，VAN GOOL L，WILLIAMS C K I，et al.The pascal visual object classes（voc） challenge[J].International Journal of Computer Vision，2010，88（2）：303-338.
[9] WANG B，ZHANG L，WEN L，et al.Towards real-world prohibited item detection：a large-scale X-ray benchmark[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2021：5412-5421.
[10] 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.
[11] 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.
[12] ZHANG X，ZENG H，GUO S，et al.Efficient long-range attention network for image super-resolution[J].arXiv：2203.06697，2022.
[13] WADEKAR S N，CHAURASIA A.Mobilevitv3：mobile-friendly vision transformer with simple and effective fusion of local，global and input features[J].arXiv：2209.
15159，2022.
[14] VASWANI A，SHAZEER N，PARMAR N，et al.Attention is all you need[J].arXiv：1706.03762，2017.
[15] MIAO C，XIE L，WAN F，et al.SIXray：a large-scale security inspection X-ray benchmark for prohibited item discovery in overlapping images[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：2119-2128.
[16] TAO R，WEI Y，JIANG X，et al.Towards real-world X-ray security inspection：a high-quality benchmark and lateral inhibition module for prohibited items detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2021：10923-10932.
[17] DOSOVITSKIY A，BEYER L，KOLESNIKOV A，et al.An image is worth 16x16 words：transformers for image recognition at scale[J].arXiv：2010.11929，2020.
[18] 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 IEEE/CVF International Conference on Computer Vision，2021：2778-2788.
[19] HOU Q，ZHOU D，FENG J.Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：13713-13722.
[20] ZHANG H，CISSE M，DAUPHIN Y N，et al.Mixup：beyond empirical risk minimization[J].arXiv：1710.09412，2017.
[21] YUN S，HAN D，OH S J，et al.Cutmix：regularization strategy to train strong classifiers with localizable features[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：6023-6032.
[22] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.YOLOv4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[23] 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.
[24] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision.Cham：Springer，2016：21-37.
[25] REDMON J，FARHADI A.YOLOv3：an incremental improvement[J].arXiv：1804.02767，2018.
[26] TIAN Z，SHEN C，CHEN H，et al.Fcos：fully convolutional one-stage object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：9627-9636.
[27] WEI Y，TAO R，WU Z，et al.Occluded prohibited items detection：an X-ray security inspection benchmark and de-occlusion attention module[C]//Proceedings of the 28th ACM International Conference on Multimedia，2020：138-146.
[28] LI B，LIU Y，WANG X.Gradient harmonized single-stage detector[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2019：8577-8584.
[29] GE Z，LIU S，WANG F，et al.YOLOx：exceeding YOLO series in 2021[J].arXiv：2107.08430，2021.
[30] SELVARAJU R R，COGSWELL M，DAS A，et al.Grad-cam：visual explanations from deep networks via gradient-based localization[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：618-626.
[31] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[32] 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，2018.
[33] HOWARD A，SANDLER M，CHU G，et al.Searching for mobilenetv3[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：1314-1324.
[34] HUANG G，LIU Z，VAN DER MAATEN L，et al.Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：4700-4708.