Object Detection for Hazardous Material Vehicles Based on Improved YOLOv5 Algorithm

被引:11
作者
Zhu, Pengcheng [1 ]
Chen, Bolun [1 ,2 ]
Liu, Bushi [1 ]
Qi, Zifan [1 ]
Wang, Shanshan [1 ]
Wang, Ling [1 ]
机构
[1] Huaiyin Inst Technol, Fac Comp & Software Engn, Huaian 223003, Peoples R China
[2] Univ Fribourg, Dept Phys, CH-1700 Fribourg, Switzerland
基金
英国科研创新办公室; 中国国家自然科学基金;
关键词
hazardous material vehicles; object detection; YOLOv5; attention mechanism; NETWORK;
D O I
10.3390/electronics12051257
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Hazardous material vehicles are a non-negligible mobile source of danger in transport and pose a significant safety risk. At present, the current detection technology is well developed, but it also faces a series of challenges such as a significant amount of computational effort and unsatisfactory accuracy. To address these issues, this paper proposes a method based on YOLOv5 to improve the detection accuracy of hazardous material vehicles. The method introduces an attention module in the YOLOv5 backbone network as well as the neck network to achieve the purpose of extracting better features by assigning different weights to different parts of the feature map to suppress non-critical information. In order to enhance the fusion capability of the model under different sized feature maps, the SPPF (Spatial Pyramid Pooling-Fast) layer in the network is replaced by the SPPCSPC (Spatial Pyramid Pooling Cross Stage Partial Conv) layer. In addition, the bounding box loss function was replaced with the SIoU loss function in order to effectively speed up the bounding box regression and enhance the localization accuracy of the model. Experiments on the dataset show that the improved model has effectively improved the detection accuracy of hazardous chemical vehicles compared with the original model. Our model is of great significance for achieving traffic accident monitoring and effective emergency rescue.
引用
收藏
页数:16
相关论文
共 32 条
  • [1] Real-Time Fuel Truck Detection Algorithm Based on Deep Convolutional Neural Network
    Alsanad, Hamid R.
    Ucan, Osman N.
    Ilyas, Muhammad
    Khan, Atta Ur Rehman
    Bayat, Oguz
    [J]. IEEE ACCESS, 2020, 8 : 118808 - 118817
  • [2] Bochkovskiy A., 2020, P IEEE CVF C COMP VI, P17
  • [3] CARL-D: A vision benchmark suite and large scale dataset for vehicle detection and scene segmentation
    Butt, Muhammad Atif
    Riaz, Faisal
    [J]. SIGNAL PROCESSING-IMAGE COMMUNICATION, 2022, 104
  • [4] Fast vehicle detection algorithm in traffic scene based on improved SSD
    Chen, Zhichao
    Guo, Haoqi
    Yang, Jie
    Jiao, Haining
    Feng, Zhicheng
    Chen, Lifang
    Gao, Tao
    [J]. MEASUREMENT, 2022, 201
  • [5] Vehicle detection using improved region convolution neural network for accident prevention in smart roads
    Djenouri, Youcef
    Belhadi, Asma
    Srivastava, Gautam
    Djenouri, Djamel
    Lin, Jerry Chun-Wei
    [J]. PATTERN RECOGNITION LETTERS, 2022, 158 : 42 - 47
  • [6] A lightweight vehicles detection network model based on YOLOv5
    Dong, Xudong
    Yan, Shuai
    Duan, Chaoqun
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2022, 113
  • [7] Time dynamics of emergency response network for hazardous chemical accidents: A case study in China
    Du, Lei
    Feng, Yingbin
    Tang, LiYaning
    Lu, Wei
    Kang, Wei
    [J]. JOURNAL OF CLEANER PRODUCTION, 2020, 248
  • [8] Gevorgyan Z., 2022, ARXIV
  • [9] Hazardous chemical leakage accidents and emergency evacuation response from 2009 to 2018 in China: A review
    Hou, Jie
    Gai, Wen-mei
    Cheng, Wu-yi
    Deng, Yun-feng
    [J]. SAFETY SCIENCE, 2021, 135
  • [10] Ju M., 2020, P 2020 3 INT C ALGOR, P1