[1]陈柏生,陈锻生.联合时空特征的车辆跟踪[J].华侨大学学报(自然科学版),2008,29(2):222-224.[doi:10.11830/ISSN.1000-5013.2008.02.0222]
　CHEN Bai-sheng,CHEN Duan-sheng.Tracking Vehicles Based on Spatio-Temporal Analysis[J].Journal of Huaqiao University(Natural Science),2008,29(2):222-224.[doi:10.11830/ISSN.1000-5013.2008.02.0222]
点击复制

联合时空特征的车辆跟踪()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第29卷
期数:
2008年第2期
页码:
222-224
栏目:
出版日期:
2008-04-20

文章信息/Info

Title:
Tracking Vehicles Based on Spatio-Temporal Analysis
文章编号:
1000-5013(2008)02-0222-03
作者:
陈柏生; 陈锻生
华侨大学信息科学与工程学院; 华侨大学信息科学与工程学院 福建泉州362021; 福建泉州362021
Author(s):
CHEN Bai-sheng;  CHEN Duan-sheng
College of Information Science and Engineering, Huaqiao University, Quanzhou 362021, China
关键词:
灰度分布差异;  路径偏差函数;  运动模式相关度;  车辆跟踪
Keywords:
intensity distribution difference;  path deviation function;  motion mode correlation;  vehicle tracking
分类号:
TP391.41
DOI:
10.11830/ISSN.1000-5013.2008.02.0222
文献标志码:
A
摘要:
提出一种联合空间特征和时间特征的匹配准则,以实现对道路车辆的跟踪.计算目标区域与候选区域的加权累积灰度分布差异,结合运动的路径连续性特征来构造运动模式相关函数,以此作为目标匹配的判据.引入虚轨迹点补偿由于目标遮挡和检测失败等导致丢失的运动轨迹点,以实现对目标连续的、完整的跟踪.实验结果表明,算法能够实现多车辆的鲁棒跟踪,并且能够较好地解决目标相互遮挡下的跟踪问题.
Abstract:
A scheme combining temporal and spatial features to track vehicles is proposed.By calculating a weighted sum of absolute intensity difference between pixels in target region and the corresponding pixels in the candidate region,motion mode correlation function is constructed with integration of path deviation function to perform the task of object matching.Phantom points are introduced to compensate the lost tracking points causing by the occlusion or object detection failure in order to maintain the trajectory complete.Experimental results show that the method can realize multiple vehicles robust tracking simultaneously,and track the vehicles under occlusion successfully.

参考文献/References:

[1] SYLVIA G, RUGGERO M, THIERRY P. Feature selection for object tracking in traffic scenes, TR-94-060 [R]. Geneva:University of Geneva, 1994.
[2] KATO J, WATANABE T, JOGA S. An HMM/MRF-based stochastic framework for robust vehicle tracking [J]. IEEE Transactions on Intelligent Transportation Systems, 2004(3):142-154.
[3] HARITAOGLU I, HARWOOD D, DAVIS L. W4:Real-time surveillance of people and their activities [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000(8):809-830.doi:10.1109/34.868683.
[4] COLLINS R T, LIPTON A J. A system for video surveillance and monitoring, CMU-RI-TR-0012 [R]. Pittsburgh:Carnegie Mellon Universit, 2000.
[5] PANG C C C, LAM W W L, YUNG N H C. A novel method for resolving vehicle occlusion in a monocular traffic-image sequence [J]. IEEE Transactions on Intelligent Transportation Systems, 2004(3):129-141.doi:10.1109/TITS.2004.833769.
[6] SONKA M, HKAVAC V, BOYL R, 艾海舟. 图像处理、分析与机器视觉 [M]. 北京:人民邮电出版社, 2003.

备注/Memo

备注/Memo:
福建省自然科学基金资助项目(A0510020); 福建省青年科技人才创新项目(2006F3086)
更新日期/Last Update: 2014-03-23