Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (14): 218-220.DOI: 10.3778/j.issn.1002-8331.2010.14.065

• 工程与应用 • Previous Articles     Next Articles

Vehicle tracking research based on computer vision

ZENG Zhi-chao,HE Xiao-hai,LV Rui,SHEN Hong   

  1. College of Electronics and Information Engineering,Sichuan University,Chengdu 610064,China
  • Received:2008-12-29 Revised:2009-03-13 Online:2010-05-11 Published:2010-05-11
  • Contact: ZENG Zhi-chao

基于计算机视觉的车辆跟踪研究

曾志超,何小海,吕 瑞,申 洪   

  1. 四川大学 电子信息学院 图像信息研究所,成都 610064
  • 通讯作者: 曾志超

Abstract: Vision-based object segment and tracking is broadly applied for video surveillance.In this paper,an object segment and shadow elimination algorithm with background image updating is proposed to eliminate shadow in HSV color space.And then a vehicle tracking method based on Kalman filtering and motion estimating is presented and the vehicle tracking effect is improved.Finally,some experiment results about vehicle segment and tracking are given.

Key words: vehicle segment, vehicle tracking, shadow elimination, Kalman filter, motion estimating

摘要: 基于计算机视觉的目标分割和跟踪被广泛应用于视频监控。首先在HSV空间利用阴影消除算法结合动态背景自适应更新技术分割目标,相比背景差分法提高了目标分割的抗干扰性。对分割出来的目标,将基于运动估计的卡尔曼滤波器应用于多个车辆目标的跟踪,提高了跟踪的速度和效果。最后给出运动车辆的分割和跟踪的实验结果。

关键词: 车辆分割, 车辆跟踪, 阴影消除, 卡尔曼滤波, 运动估计

CLC Number: