[1]张子恒,肖 建*,王新宇,等.基于 MobileNet_SSD 的交通违章检测系统[J].计算机技术与发展,2021,31(11):64-70.[doi:10. 3969 / j. issn. 1673-629X. 2021. 11. 011]
　ZHANG Zi-heng,XIAO Jian*,WANG Xin-yu,et al.A Traffic Violation Detection System Based on MobileNet_SSD[J].,2021,31(11):64-70.[doi:10. 3969 / j. issn. 1673-629X. 2021. 11. 011]
点击复制

基于 MobileNet_SSD 的交通违章检测系统()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年11期
页码:
64-70
栏目:
图形与图像
出版日期:
2021-11-10

文章信息/Info

Title:
A Traffic Violation Detection System Based on MobileNet_SSD
文章编号:
1673-629X(2021)11-0064-07
作者:
张子恒; 肖 建* ; 王新宇; 章佳琪; 许 杰
南京邮电大学 电子与光学工程学院、微电子学院,江苏 南京 210003
Author(s):
ZHANG Zi-heng; XIAO Jian* ; WANG Xin-yu; ZHANG Jia-qi; XU Jie
School of Electronic and Optical Engineering,School of Microelectronics,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
关键词:
MobileNet_SSD; 目标检测; 车辆追踪; 违章检测; 智能交通
Keywords:
MobileNet_SSD; object detection; vehicle track; violation detection; intelligent transportation
分类号:
TP302
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 11. 011
摘要:
随着国内机动车保有量的持续增长, 城市道路交通运转压力急剧增强。 在现有交通管理系统中, 通常采用图像处理算法检测机动车违章行为。 但基于图像处理算法的违章检测系统存在计算量大、不适用于嵌入式设备和复杂场景下检测精度下降等问题,为系统在实际中的应用带来了一定的限制。针对该问题, 将深度学习算法引入检测系统中, 提出了基于 MobileNet_SSD 的路口交通违章检测系统。以 MobileNet_SSD 网络检测车辆,结合帧间欧氏距离算法追踪车辆轨迹,制定违章行为判定策略,实现对 5 种机动车违章行为的检测及取证。 在 EAIDK-610 的开发平台下,车辆识别 mAP 约为83. 18% ,违章检测准确率约为 97% ,系统运行速度约为 8. 31 FPS。 实验结果表明,系统不仅提升了在嵌入式设备上的检测速度,同时对复杂场景的检测具有较好的鲁棒性。
Abstract:
With the continuous growth of car parc in China,the pressure of urban road traffic operation increases sharply. In the existing traffic management system,image processing algorithm is usually used to detect car violations. However,the violation detection system based on image processing algorithm has many problems,such as large computation,not suitable for embedded devices and low detection accuracy in complex environment, which brings some limitations to the practical application of the system. To solve this problem,the deep learning algorithm is introduced into the detection system and a traffic violation detection system based on MobileNet_SSD is proposed. The MobileNet_ SSD network is used to detect cars, and the inter - frame Euclidean distance algorithm is adopted to track vehicle tracks. The determination strategy of violation behaviors is developed to detect and collect evidence of five kinds of motor vehicle violations. On the EAIDK-610 development platform,the vehicle identification mAP is about 83. 18% ,the violation detection accuracy rate is 97% ,and the system running speed is 8. 31 FPS. The experiment shows that this system not only improves the detection speed on embedded devices,but also has better robustness for detection of complex scenes.

相似文献/References:

[1]刘晓明 李毓蕙 高燕 郑华强.基于目标区域清晰显示的H.264编码策略[J].计算机技术与发展,2010,(06):29.
　LIU Xiao-ming,LI Yu-hui,GAO Yan,et al.A Coding Strategy of H.264 Based on High-definition Display of Target Region[J].,2010,(11):29.
[2]刘翔 吴谨 祝愿博 康晓晶.基于视频序列的目标检测与跟踪技术研究[J].计算机技术与发展,2009,(11):179.
　LIU Xiang,WU Jin,ZHU Yuan-bo,et al.A Study of Object Detecting and Tracking Based on Video Sequences[J].,2009,(11):179.
[3]曙光 张超 蔡则苏.基于改进的混合高斯模型的目标检测方法[J].计算机技术与发展,2012,(07):60.
　SHU Guang,ZHANG Chao,CAI Ze-su.Target Detection Method Based on Improved Gaussian Mixture Model[J].,2012,(11):60.
[4]刘洁,李目,周少武.一种混沌混合粒子群优化RBF神经网络算法[J].计算机技术与发展,2013,(08):181.
　LIU Jie[],LI Mu[],ZHOU Shao-wu[].An Algorithm of Chaotic Hybrid Particle Swarm Optimization Based on RBF Neural Network[J].,2013,(11):181.
[5]蒋翠清,孙富亮,吴艿芯. 基于相对欧氏距离的背景差值法视频目标检测[J].计算机技术与发展,2015,25(01):37.
　JIANG Cui-qing,SUN Fu-liang,WU Nai-xin. Video Object Detection of Background Subtraction Method Based on Relative Euclidean Distance[J].,2015,25(11):37.
[6]卢官明,衣美佳. 步态识别关键技术研究[J].计算机技术与发展,2015,25(07):100.
　LU Guan-ming,YI Mei-jia. Research on Critical Techniques in Gait Recognition[J].,2015,25(11):100.
[7]高翔,朱婷婷,刘洋. 多摄像头系统的目标检测与跟踪方法研究[J].计算机技术与发展,2015,25(07):221.
　GAO Xiang,ZHU Ting-ting,LIU Yang. Research of Target Detection and Tracking Method for Multi-camera System[J].,2015,25(11):221.
[8]章文洁[][],黄旻[],张桂峰[]. 滤光片多光谱成像中运动目标场景误配准修正[J].计算机技术与发展,2016,26(01):18.
　ZHANG Wen-jie[][],HUANG Min[],ZHANG Gui-feng[]. Misregistration Correction for Moving Object Scene in Filter-type Multispectral Imaging[J].,2016,26(11):18.
[9]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(11):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[10]张夏清,茅耀斌. 一种改进的ViBe背景提取算法[J].计算机技术与发展,2016,26(07):36.
　ZHANG Xia-qing,MAO Yao-bin. An Improved ViBe Background Generation Method[J].,2016,26(11):36.

更新日期/Last Update: 2021-11-10