面向车辆目标的路侧多摄像机双向匹配交接方法

doi:10.19562/j.chinasae.qcgc.2021.10.003

汽车工程 ›› 2021, Vol. 43 ›› Issue (10): 1435-1441.doi: 10.19562/j.chinasae.qcgc.2021.10.003

面向车辆目标的路侧多摄像机双向匹配交接方法

陈明^1,²,武一民¹,高博麟²(),郑凯元^1,²

^1.河北工业大学机械工程学院，天津 300130
^2.清华大学车辆与运载学院，北京 100084

收稿日期:2021-05-18 修回日期:2021-07-03 出版日期:2021-10-25 发布日期:2021-10-25
通讯作者: 高博麟 E-mail:gaobolin@tsinghua.edu.cn
基金资助:
广东省重点领域研发计划项目(2019B090912001);清华大学-滴滴未来出行联合研究中心项目资助

Vehicle Target Oriented Bidirectional Matching Handover Method for Multi Camera on Roadside

Ming Chen^1,²,Yimin Wu¹,Bolin Gao²(),Kaiyuan Zheng^1,²

^1.School of Mechanical Engineering，Hebei University of Technology，Tianjin 300130
^2.School of Vehicle and Mobility，Tsinghua University，Beijing 100084

Received:2021-05-18 Revised:2021-07-03 Online:2021-10-25 Published:2021-10-25
Contact: Bolin Gao E-mail:gaobolin@tsinghua.edu.cn

摘要/Abstract

摘要：

路侧传感器由于视野角度高，探测范围广，有利于观察目标间的时空位置关系和运动趋势，成为支撑车路云一体化融合系统的重要感知手段。然而当前路侧传感器存在着跨感知域的目标难以被连续跟踪的挑战，为了解决车辆目标在摄像机交叉视角间的目标交接问题，针对路侧感知重叠视野提出了双向匹配目标交接方法：建立摄像机间变换关系对重叠域内车辆目标进行投影，设计匹配约束机制解决匹配冲突难题，基于目标双向投影设计双向匹配策略，根据匹配矩阵标识符与颜色相似度输出交接结果。经路侧实验数据验证，提出的方法可有效应用于典型城市道路交通场景，相比于单向匹配方法，路段场景漏匹配降低22.22%，误匹配降低28.57%；路口场景漏匹配降低28.89%，误匹配降低44.00%，具有良好的准确性和可靠性。

关键词: 车路云一体化, 路侧相机, 重叠视野, 目标交接, 双向匹配

Abstract:

Because of the high field of view angle and wide detection range， roadside sensor is conducive to observe the spatial?temporal relationship and movement trend of targets， and becomes an important sensing means to support the vehicle road cloud integration system. However， the current roadside sensor faces the challenge that it is difficult to continuously track the target motion across the sensing domain. In order to solve the problem of target handover between cross view cameras， a bi?directional matching target handover method is proposed for roadside sensing overlapped field of vision. The transformation relationship between cameras is established to project the vehicle target in the overlapped domain， and the matching constraint mechanism is designed to solve the problem of matching conflict. The bidirectional matching strategy is designed based on the bidirectional projection of the target， and the handover result is output according to the matching matrix identifier and color similarity. The roadside experimental data show that the proposed method can be effectively applied to typical urban road traffic scenes. Compared with the one?way matching method， it reduces the missing matching by 22.22% and the false matching by 28.57% for road scenes； The missing matching and false matching of intersection scenes are reduced by 28.89% and 44.00%， respectively， which has good accuracy and reliability.

Key words: vehicle?road?cloud integration, roadside camera, overlapping field of view, target handover, bidirectional matching

陈明,武一民,高博麟,郑凯元. 面向车辆目标的路侧多摄像机双向匹配交接方法[J]. 汽车工程, 2021, 43(10): 1435-1441.

Ming Chen,Yimin Wu,Bolin Gao,Kaiyuan Zheng. Vehicle Target Oriented Bidirectional Matching Handover Method for Multi Camera on Roadside[J]. Automotive Engineering, 2021, 43(10): 1435-1441.

图/表 10

图1

图2

图3

图4

图5

图6

图7

表1

图8

表2

参考文献 18

1	李克强，常雪阳，李家文，等. 智能网联汽车云控系统及其实现［J］. 汽车工程， 2020， 42（12）： 1595-1605.
	LI K Q， CHANG X Y， LI J W， et al. Cloud control system for intelligent and connected vehicles and its application［J］. Automotive Engineering， 2020， 42（12）： 1595-1605.
2	霍阔，李长云，李妍，等. 一种重叠视域多摄像机环境下的运动目标匹配SHFSM算法［J］. 计算机应用研究， 2013， 30（2）： 619-622.
	HUO K， LI C Y， LI Y， et al. Algorithm named SHFSM about multi⁃camera moving object matching in overlapping fields of view［J］. Application Research of Computers， 2013， 30（2）： 619-622.
3	STARK M， SCHIELE B. How good are local features for classes of geometric objects［C］. IEEE International Conference on Computer Vision， 2007：1-8.
4	黄新，黄柏华，熊显名. 基于改进ORB算法无重叠视野域的目标交接［J］. 液晶与显示， 2016， 31（8）： 810-817.
	HUANG X， HUANG B H， XIONG X M. Target handoff based on improved ORB algorithm on non⁃overlapping cameras［J］. Liquid Crystals and Displays， 2016， 31（8）： 810-817.
5	ZHAO T， AGGARWAL M， KUMAR R， et al. Real⁃time wide area multi⁃camera stereo tracking［C］. IEEE Conference on Computer Vision and Pattern Recognition， 2005：976-983.
6	邓颖娜，朱虹，李刚，等. 基于场景模型的多摄像机目标跟踪算法［J］. 计算机工程与应用， 2008（5）： 55-57.
	DENG Y N， ZHU H， LI G， et al. Multi camera target tracking algorithm based on scene model［J］. Computer Engineering and Applications， 2008（5）： 55-57.
7	KHAN S， SHAH M. Consistent labeling of tracked objects in multiple cameras with overlapping fields of view［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2003， 25（10）： 1355-1360.
8	牛恩国，程咏梅，潘泉，等. 多摄像机视野分界线快速自动生成算法［J］. 计算机应用研究， 2007（3）： 297-299.
	NIU E G， CHENG Y M， PAN Q， et al. Fast algorithm for automatic generating field of view line of multiple cameras［J］. Application Research of Computer， 2007（3）： 297-299.
9	YANG J， ZHANG J， WU W. Recovering camera field of view lines by using SIFT algorithm and homograph［C］. IEEE World Automation Congress， 2012： 1-4.
10	谢月飞，蔡晓东，张学敏. 基于透视投影变换与动态候选策略的目标交接算法［J］. 计算机应用， 2013， 33（S1）： 170-173.
	XIE Y F， CAI X D， ZHANG X M. Target handoff algorithm based on perspective projection transformation and dynamic candidate strategy［J］. Computer Applications， 2013， 33（S1）： 170-173.
11	YAN M， ZHAO Y， LIU M， et al. High⁃speed moving target tracking of multi⁃camera system with overlapped field of view［J］. Signal Image and Video Processing， 2021，15： 1-9.
12	佟强，王紫瑶，杨大利，等. 利用单应变换与对极约束的基础矩阵估计算法［J］. 郑州大学学报（理学版）， 2021， 53（1）： 61-67.
	TONG Q， WANG Z Y， YANG D L， et al. Fundamental matrix estimation algorithm based on homography transformation and epipolar constraint［J］. Journal of Zhengzhou University（Natural Science Edition）， 2021， 53（1）： 61-67.
13	KHAN S， SHAH M. A multiview approach to tracking people in crowded scenes using a planar homography constraint［C］. European Conference on Computer Vision， 2006： 133-146.
14	陈政宏，李爱娟，王希波，等. 基于改进Hough变换的结构化道路车道线识别［J］. 科学技术与工程， 2020， 20（26）： 10829-10834.
	CHEN Z H， LI A J， WANG X B， et al. Structured road lane line recognition based on improved hough transformation［J］. Science Technology and Engineering， 2020， 20（26）： 10829-10834.
15	HE Y， WEI X， HONG X， et al. Multi⁃target multi⁃camera tracking by tracklet⁃to⁃target assignment［J］. IEEE Transactions on Image Processing， 2020，29： 5191-5205.
16	秦绪佳，程燕飞，范颖琳，等. 基于三边滤波的HSV色彩空间Retinex图像增强算法［J］. 小型微型计算机系统， 2016， 37（1）： 168-172.
	QIN X J， CHENG Y F， FAN Y L， et al. Image enhancement algorithm based on retinex of trilateral filter in HSV color space［J］. Journal of Chinese Mini⁃Micro Computer Systems， 2016， 37（1）： 168-172.
17	SHEN K T， YAP V V， NISAR H. A non⁃overlapping view human tracking algorithm using HSV color space［C］. International Conference on Green and Human Information Technology， 2019： 97-102.
18	KUO C H， HUANG C， NEVATIA R. Inter⁃camera association of multi⁃target tracks by on⁃line learned appearance affinity models［C］. European Conference on Computer Vision， 2010：5-11.

面向车辆目标的路侧多摄像机双向匹配交接方法

Vehicle Target Oriented Bidirectional Matching Handover Method for Multi Camera on Roadside

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 18

相关文章 0

Metrics

本文评价

推荐阅读 10

项目	单向匹配	本文方法	效果提升
漏匹配	9	7	22.22%
误匹配	7	5	28.57%

项目	单向匹配	本文方法	效果提升
漏匹配	45	32	28.89%
误匹配	25	14	44.00%