基于实时交通状况和自适应像素分割的运动车辆检测

孙敏; 李免; 赵玉舟; 孙伟; 张小瑞

doi:10.37188/CJLCD.2020-0316

您当前的位置：

首页 >

文章列表页 >

基于实时交通状况和自适应像素分割的运动车辆检测

图像处理 | 更新时间：2021-09-30

- 基于实时交通状况和自适应像素分割的运动车辆检测
- Vehicle detection based on real-time traffic condition and adaptive pixel segmentation
- 液晶与显示 2021年36卷第10期页码：1454-1462
- 作者机构：
  
  1.南京信息工程大学自动化学院, 江苏南京 210044
  2.江苏省大气环境与装备技术协同创新中心, 江苏南京 210044
  3.南京信息工程大学无锡研究院, 江苏无锡 214100
- 作者简介：
  
  [ "孙敏(1999-), 女, 江苏徐州人, 本科在读, 主要从事计算机视觉, 车辆跟踪方面的研究。E-mail:863060894@qq.com" ]
  [ "孙伟(1980-), 男, 河南内乡人, 博士, 副教授, 2010年于东南大学获得博士学位, 主要从事计算机视觉, 道路环境感知, 车辆检测和重识别方面的研究.E-mail: sunw0125@163.com" ]
- 基金信息：
  
  国家自然科学基金(61304205);国家自然科学基金(61502240);江苏省自然科学基金(BK20191401);江苏省自然科学基金(BK20201136);大学生实践创新训练计划(202010300290);大学生实践创新训练计划(202010300211);大学生实践创新训练计划(202010300116E);南京信息工程大学本科生优秀毕业设计（论文）支持计划
- DOI：10.37188/CJLCD.2020-0316
  中图分类号： TP391.41;U463.6
- 收稿日期：2020-11-30，
  
  修回日期：2021-02-20，
  
  纸质出版日期：2021-10
- 稿件说明：
移动端阅览
孙敏, 李免, 赵玉舟, 等. 基于实时交通状况和自适应像素分割的运动车辆检测[J]. 液晶与显示, 2021,36(10):1454-1462.

Min SUN, Mian LI, Yu-zhou ZHAO, et al. Vehicle detection based on real-time traffic condition and adaptive pixel segmentation[J]. Chinese journal of liquid crystals and displays, 2021, 36(10): 1454-1462.
孙敏, 李免, 赵玉舟, 等. 基于实时交通状况和自适应像素分割的运动车辆检测[J]. 液晶与显示, 2021,36(10):1454-1462. DOI： 10.37188/CJLCD.2020-0316.

Min SUN, Mian LI, Yu-zhou ZHAO, et al. Vehicle detection based on real-time traffic condition and adaptive pixel segmentation[J]. Chinese journal of liquid crystals and displays, 2021, 36(10): 1454-1462. DOI： 10.37188/CJLCD.2020-0316.

摘要

车辆检测是车辆识别和跟踪的重要前提。为解决传统车辆检测算法无法兼顾检测的准确性与实时性的问题，本文提出一种基于实时交通状况和自适应像素分割的运动车辆检测算法。该算法采用多帧间隔图像建立初始背景模型，提出基于时-空变化度的背景区域变化评价方法，并基于时-空变化度制订了自适应的学习率更新策略。通过设置一个信任区间，并根据当前交通状况和像素点是否处于信任区间内来判断当前的背景模型是否需要更新，进而实现对运动车辆的准确、快速检测。改进后的像素自适应分割算法在不同场景中检测的性能指标Recall、Precision和F-measure分别达到0.929，0.864，0.888，均高于传统像素自适应分割算法，且算法的处理时间为88.37 ms，比传统像素自适应分割算法的运算速度快近10 ms，基本满足车辆检测所需的速度快、精度高、鲁棒性高等要求。

Abstract

In an intelligent transportation system

the vehicle detection is an important prerequisite for vehicle tracking and identification. However

the traditional vehicle detection algorithms cannot effectively maintain a balance between accuracy and real-time performance. In this paper

a new moving vehicle detection algorithm based on improved adaptive pixel segmentation is proposed. The initial background model is established based on multi frame interval image

and an evaluation method of background region change is proposed based on the spatio-temporal variation degree. Based on this

an adaptive updating strategy of learning rate is formulated. By setting a trust interval

whether the current background model needs to be updated can be adaptively determined according to the current traffic conditions and pixels whether are in the trust interval

thereby the accurate and fast detection of moving vehicles are realized. The performance indicators of Recall

Precision and F-measure of the improved adaptive pixel segmentation algorithm in different scenarios are 0.929

0.864 and 0.888

respectively

which are higher than the traditional adaptive pixel segmentation algorithm

and the processing time of the algorithm is 88.37 ms

nearly 10 ms faster than the traditional adaptive pixel segmentation algorithm. It basically meets the requirements of high speed

high precision and high robustness of vehicle detection.

关键词

Keywords

references

B K P HORN , B G SCHUNCK . "Determining optical flow": a retrospective . Artificial Intelligence , 1993 . 59 ( 1/2 ): 81 - 87 .

P RAMYA , R RAJESWARI . A modified frame difference method using correlation coefficient for background subtraction . Procedia Computer Science , 2016 . 93 478 - 485 . DOI: 10.1016/j.procs.2016.07.236 http://doi.org/10.1016/j.procs.2016.07.236 .

张小建 , 徐慧 . 基于视频处理的运动车辆检测算法的研究 . 液晶与显示 , 2012 . 27 ( 1 ): 108 - 113 . DOI: 10.3788/YJYXS20122701.0108 http://doi.org/10.3788/YJYXS20122701.0108 .

X J ZHANG , H XU . Moving vehicle detection algorithm based on video processing . Chinese Journal of Liquid Crystals and Displays , 2012 . 27 ( 1 ): 108 - 113 . DOI: 10.3788/YJYXS20122701.0108 http://doi.org/10.3788/YJYXS20122701.0108 .

王齐 , 金小峰 . 复杂环境中车辆检测与跟踪方法的研究 . 液晶与显示 , 2016 . 31 ( 5 ): 511 - 517 . DOI: 10.3788/YJYXS20163105.0511 http://doi.org/10.3788/YJYXS20163105.0511 .

Q WANG , X F JIN . Vehicle detecting and tracking method in complex environments . Chinese Journal of Liquid Crystals and Displays , 2016 . 31 ( 5 ): 511 - 517 . http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20163105.0511&graphicAbstract=0 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20163105.0511&graphicAbstract=0 .

陈华清 , 陈学文 , 周越 . 基于图像的车道线内车辆目标识别 . 汽车实用技术 , 2020 . 45 ( 19 ): 33 - 34, 47 . https://www.cnki.com.cn/Article/CJFDTOTAL-SXQC202019009.htm https://www.cnki.com.cn/Article/CJFDTOTAL-SXQC202019009.htm .

H Q CHEN , X W CHEN , Y ZHOU . Vehicle target recognition in lane line based on image . Automobile Applied Technology , 2020 . 45 ( 19 ): 33 - 34, 47 . https://www.cnki.com.cn/Article/CJFDTOTAL-SXQC202019009.htm https://www.cnki.com.cn/Article/CJFDTOTAL-SXQC202019009.htm .

A KRIZHEVSKY , I SUTSKEVER , G E HINTON . ImageNet classification with deep convolutional neural networks . Communications of the ACM , 2017 . 60 ( 6 ): 84 - 90 . DOI: 10.1145/3065386 http://doi.org/10.1145/3065386 .

REDMON J, DIVVALA S, GIRSHICK R, et al . You only look once: Unified, real-time object detection[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas, Nevada, USA: IEEE, 2016: 779-788.

邓淇天 , 李旭 . 基于多特征融合的车辆检测算法 . 传感器与微系统 , 2020 . 39 ( 6 ): 131 - 134 . https://www.cnki.com.cn/Article/CJFDTOTAL-CGQJ202006039.htm https://www.cnki.com.cn/Article/CJFDTOTAL-CGQJ202006039.htm .

Q T DENG , X LI . Vehicle detection algorithm based on multi-feature fusion . Transducer and Microsystem Technologies , 2020 . 39 ( 6 ): 131 - 134 . https://www.cnki.com.cn/Article/CJFDTOTAL-CGQJ202006039.htm https://www.cnki.com.cn/Article/CJFDTOTAL-CGQJ202006039.htm .

HOFMANN M, TIEFENBACHER P, RIGOLL G. Background segmentation with feedback: the pixel-based adaptive segmenter[C]// Proceedings of 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition . Providence, RI, USA: IEEE, 2012: 38-43.

T KRYJAK , M KOMORKIEWICZ , M GORGON . Real-time foreground object detection combining the PBAS background modelling algorithm and feedback from scene analysis module . International Journal of Electronics and Telecommunications , 2014 . 60 ( 1 ): 61 - 72 . http://ijet.czasopisma.pan.pl/images/data/ijet/wydania/No_1_2014/6%20eletel-2014-0006.pdf http://ijet.czasopisma.pan.pl/images/data/ijet/wydania/No_1_2014/6%20eletel-2014-0006.pdf .

K MUCHTAR , F RAHMAN , T W CENGGORO , 等 . An improved version of texture-based foreground segmentation: block-based adaptive segmenter . Procedia Computer Science , 2018 . 135 579 - 586 . DOI: 10.1016/j.procs.2018.08.228 http://doi.org/10.1016/j.procs.2018.08.228 .

孙渊 , 侯进 . 基于改进PBAS算法的级联特征行车检测 . 计算机应用研究 , 2019 . 36 ( 11 ): 3481 - 3485 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ201911064.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ201911064.htm .

Y SUN , J HOU . Vehicle detection using cascaded feature based on improved PBAS algorithm . Application Research of Computers , 2019 . 36 ( 11 ): 3481 - 3485 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ201911064.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ201911064.htm .

J M MILLA , S L TORAL , M VARGAS , 等 . Dual-rate background subtraction approach for estimating traffic queue parameters in urban scenes . IET Intelligent Transport Systems , 2013 . 7 ( 1 ): 122 - 130 . DOI: 10.1049/iet-its.2012.0020 http://doi.org/10.1049/iet-its.2012.0020 .

李浩 , 张运胜 . 基于反馈背景模型的城市道路交叉口前景目标检测 . 交通运输系统工程与信息 , 2017 . 17 ( 6 ): 63 - 69 . https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201706010.htm https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201706010.htm .

H LI , Y S ZHANG . Foreground objects in surveillance video of urban traffic intersection using feedback background subtraction model . Journal of Transportation Systems Engineering and Information Technology , 2017 . 17 ( 6 ): 63 - 69 . https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201706010.htm https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201706010.htm .

Y WU , J LIM , M YANG . Object tracking benchmark . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015 . 37 ( 9 ): 1834 - 1848 . DOI: 10.1109/TPAMI.2014.2388226 http://doi.org/10.1109/TPAMI.2014.2388226 .

L C OUYANG , H L WANG . Vehicle target detection in complex scenes based on YOLOv3 algorithm . IOP Conference Series: Materials Science and Engineering , 2019 . 569 ( 5 ): 052018 .

浏览量

157

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于改进YOLOx的弱光照环境车辆检测方法

融合毫米波雷达与机器视觉的雾天车辆检测