计算机科学 ›› 2021, Vol. 48 ›› Issue (12): 256-263.doi: 10.11896/jsjkx.200700026

• 计算机图形学&多媒体 • 上一篇    下一篇

夜间行驶车辆远光灯检测方法

龚航, 刘培顺   

  1. 中国海洋大学信息科学与工程学院 山东 青岛266100
  • 收稿日期:2020-07-03 修回日期:2021-01-31 出版日期:2021-12-15 发布日期:2021-11-26
  • 通讯作者: 刘培顺(liups@ouc.edu.cn)
  • 作者简介:201612735@qq.com
  • 基金资助:
    国家重点研发计划基金资助项目(2017YFC0806200)

Detection Method of High Beam in Night Driving Vehicle

GONG Hang, LIU Pei-shun   

  1. College of Information Science and Engineering,Ocean University of China,Qingdao,Shandong 266100,China
  • Received:2020-07-03 Revised:2021-01-31 Online:2021-12-15 Published:2021-11-26
  • About author:GONG Hang,born in 1995,postgra-duate,is a member of China Computer Federation.His main research interests include information security and object detection.
    LIU Pei-Shun,born in 1975,Ph.D,lecturer,is a member of China Computer Federation.His main research interests include information security and deep learning.
  • Supported by:
    National Key Research and Development Project(2017YFC0806200).

摘要: 有效地对夜间车辆违规使用远光灯的行为进行管理,可以降低夜间交通事故的发生,但目前缺乏高效的远光灯检测方法,相关交通法规无法得到有效执行。针对此问题,文中提出了一种夜间车辆远光灯检测深度学习算法。该算法基于YOLOv3进行设计,通过降低各层卷积层维数的方式,来减少整体网络的参数量,提高算法的运行速度;然后对网络的残差组件进行改进,使用标准的残差组件,同时设计了一个空洞卷积模块来加强网络局部和全局特征的融合,增强了网络的特征表达能力;接着对YOLOv3的损失函数进行了改进,优化小尺寸目标对坐标损失的贡献,增强了小尺度目标的检测能力;最后对YOLOv3先验框聚类算法和个数进行优化,提高模型的表达能力和检测速度。实验结果表明,所设计的算法的平均准确率(mAP)达到了99.09%,相比YOLOv3提升了30%,满足了实用化要求,能够有效地检测违规行为。

关键词: 交通管理, 远光灯检测, 深度学习, YOLOv3, 残差网络, 空洞卷积

Abstract: Managing the illegal use of high beams can reduce the occurrence of night traffic accidents.However,at present,there is no efficient detection method for high beam of night,and relevant traffic regulations cannot be effectively implemented.In order to solve this problem,an algorithm to detect the high beam at night is proposed in this paper.Based on YOLOv3,this algorithm optimizes the network structure of YOLOv3,accelerates its operation speed,uses standard residual components and dilates convolution to enhance the feature expression ability of the network,and then the loss function of YOLOv3 is improved to optimize the contribution of small-scale target to coordinate loss,which enhances the detection ability of small-scale target,finally YOLOv3 prior frame clustering algorithm and number are optimized to improve the expression ability and detection speed of the model.The experimental results show that the mean average precision (mAP) of the algorithm designed in this paper is 99.09%,and 30% higher than that of YOLOv3.The algorithm satisfies the practical requirement and can detect the violation effectively.

Key words: Traffic management, High beam detection, Deep learning, YOLOv3, ResNet, Dilated convolution

中图分类号: 

  • TP391
[1]WU Y Q,HUA J F,CHEN Y,et al.Difficulties and Countermeasures for illegal use of driving beam headlamp of motor vehicles[J].China Public Security (Academy Edition),2018(1):78-81.
[2]GUAN Y.Look at the top ten “most offensive traffic habits” from a technical perspective[J].Auto & Safety,2014(7):56-63.
[3]SU J Y,ZHANG W W,WU X C,et al.The driving beam recognition of vehicle based on multi-structure feature extraction and trajectory tracking[J].Journal of Electronic Measurement and Instrumentation,2018,32(10):103-110.
[4]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2014:580-587.
[5]GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision.2015:1440-1448.
[6]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[C]//International Conference on Neural Information Processing Systems.Cambridge:MIT Press,2015:91-99.
[7]DAI J,LI Y,HE K,et al.R-FCN:Object detection via region-based fully convolutional networks[C]//Advances in Neural Information Pocessing Systems.2016:379-387.
[8]HE K,GKIOXARI G,DOLLAR P,et al.Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV).Venice,Italy,2017:2980-2988.
[9]REDMON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-Time Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:779-788.
[10]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shot multibox detector[C]//European Conference on Computer Vision.Cham:Springer,2016:21-37.
[11]REDMON J,FARHADI A.YOLO9000:Better,faster,stronger[C]//IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE Computer Society,2017:6517-6525.
[12]LIN T Y,GOYAL P,GIRSHICK R,et al.Focal Loss for Dense Object Detection[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2017(99):2999-3007.
[13]REDMON J,FARHADI A.YOLOv3:An incremental improve-ment[J].arXiv:1804.02767,2018.
[14]LIU S,HUANG D,WANG Y.Receptive field block net for accurate and fast object detection[C]//Computer Vision-ECCV.2018:404-419.
[15]DAI W C,JIN L X,LI G N,et al.Real-time airplane detection algorithm in remote-sensing images based on improved YOLOv3[J].Opto-Electronic Engineering,2018,45(12):84-92.
[16]ZHANG F K,YANG F,LI C.Fast Vehicle Detection Method Based on Improved YOLOv3[J].Computer Engineering and Applications,2019,55(2):12-20.
[17]ZHANG G S,GE G Y,ZHU R H,et al.Research of Gear Defect Detection Based on Improved YOLOv3 Network[J/OL].http://kns.cnki.net/kcms/detail/31.1690.TN.20191107.1704.010.html.
[18]REZATOFIGHI H,TSOI N,GWAK J Y,et al.Generalized Intersection Over Union:A Metric and a Loss for Bounding Box Regression[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2019:658-666.
[19]XU Y L,HE P.Yolov3 vehicle detection algorithm with im- proved loss function[J].Information & Communications,2019(12):4-7.
[20]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedingss of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas,NV,2016:770-778.
[21]YU F,KOLTUN V.Multi-scale context aggregation by dilated convolutions[J].arXiv:1511.07122,2015.
[22]CUI W L,WANG Y J,KANG S Q,et al.The detection method of highway lane line based on improved yolov3 algorithm[J/OL].https://doi.org/10.16383/j.aas.c190178.
[23]LI B,LIU Y,WANG X.Gradient Harmonized Single-stage Detector[J].arXiv:1811.05181,2018.
[24]BOCHKOVSKIY A,WANG C Y,LIAO H Y M.YOLOv4:Optimal Speed and Accuracy of Object Detection[J].arXiv:2004.10934,2020.
[25]LI Z X,ZHOU F Q.FSSD:feature fusion single shot multibox detector[J].arXiv:1712.00960,2017.
[1] 董晓梅, 王蕊, 邹欣开. 面向推荐应用的差分隐私方案综述[J]. 计算机科学, 2021, 48(9): 21-35.
[2] 周新民, 胡宜桂, 刘文洁, 孙荣俊. 基于多模态多层级数据融合方法的城市功能识别研究[J]. 计算机科学, 2021, 48(9): 50-58.
[3] 钱梦薇, 过弋. 融合偏置深度学习的距离分解Top-N推荐算法[J]. 计算机科学, 2021, 48(9): 103-109.
[4] 徐涛, 田崇阳, 刘才华. 基于深度学习的人群异常行为检测综述[J]. 计算机科学, 2021, 48(9): 125-134.
[5] 张新峰, 宋博. 一种基于改进三元组损失和特征融合的行人重识别方法[J]. 计算机科学, 2021, 48(9): 146-152.
[6] 袁磊, 刘紫燕, 朱明成, 马珊珊, 陈霖周廷. 融合改进密集连接和分布排序损失的遥感图像检测[J]. 计算机科学, 2021, 48(9): 168-173.
[7] 林椹尠, 张梦凯, 吴成茂, 郑兴宁. 利用生成对抗网络的人脸图像分步补全法[J]. 计算机科学, 2021, 48(9): 174-180.
[8] 黄晓生, 徐静. 基于PCANet的非下采样剪切波域多聚焦图像融合[J]. 计算机科学, 2021, 48(9): 181-186.
[9] 田野, 陈宏巍, 王法胜, 陈兴文. 室内移动机器人的SLAM算法综述[J]. 计算机科学, 2021, 48(9): 223-234.
[10] 谢良旭, 李峰, 谢建平, 许晓军. 基于融合神经网络模型的药物分子性质预测[J]. 计算机科学, 2021, 48(9): 251-256.
[11] 冯霞, 胡志毅, 刘才华. 跨模态检索研究进展综述[J]. 计算机科学, 2021, 48(8): 13-23.
[12] 王立梅, 朱旭光, 汪德嘉, 张勇, 邢春晓. 基于深度学习的民事案件判决结果分类方法研究[J]. 计算机科学, 2021, 48(8): 80-85.
[13] 郭琳, 李晨, 陈晨, 赵睿, 范仕霖, 徐星雨. 基于通道注意递归残差网络的图像超分辨率重建[J]. 计算机科学, 2021, 48(8): 139-144.
[14] 刘帅, 芮挺, 胡育成, 杨成松, 王东. 基于深度学习SuperGlue算法的单目视觉里程计[J]. 计算机科学, 2021, 48(8): 157-161.
[15] 王施云, 杨帆. 基于U-Net特征融合优化策略的遥感影像语义分割方法[J]. 计算机科学, 2021, 48(8): 162-168.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 于义科,郑雪峰,韩晓光,刘行兵. 一个标准模型下基于身份的高效代理签名方案[J]. 计算机科学, 2011, 38(6): 133 -139 .
[2] 刘志, 潘晓彬. 基于渲染图像角度结构特征的三维模型检索方法[J]. 计算机科学, 2018, 45(11A): 251 -255 .
[3] 杜婉茹, 王潇茵, 田涛, 张越. 面向未知环境及动态障碍的人工势场路径规划算法[J]. 计算机科学, 2021, 48(2): 250 -256 .
[4] 肖蕾, 陈荣赏, 缪淮扣, 洪煜. 融合聚类算法和缺陷预测的测试用例优先排序方法[J]. 计算机科学, 2021, 48(5): 99 -108 .
[5] 潘孝勤, 芦天亮, 杜彦辉, 仝鑫. 基于深度学习的语音合成与转换技术综述[J]. 计算机科学, 2021, 48(8): 200 -208 .
[6] 王俊, 王修来, 庞威, 赵鸿飞. 面向科技前瞻预测的大数据治理研究[J]. 计算机科学, 2021, 48(9): 36 -42 .
[7] 余力, 杜启翰, 岳博妍, 向君瑶, 徐冠宇, 冷友方. 基于强化学习的推荐研究综述[J]. 计算机科学, 2021, 48(10): 1 -18 .
[8] 王梓强, 胡晓光, 李晓筱, 杜卓群. 移动机器人全局路径规划算法综述[J]. 计算机科学, 2021, 48(10): 19 -29 .
[9] 高洪皓, 郑子彬, 殷昱煜, 丁勇. 区块链技术专题序言[J]. 计算机科学, 2021, 48(11): 1 -3 .
[10] 毛瀚宇, 聂铁铮, 申德荣, 于戈, 徐石成, 何光宇. 区块链即服务平台关键技术及发展综述[J]. 计算机科学, 2021, 48(11): 4 -11 .