摘要
基于视频的自动目标检测和跟踪是计算机视觉中一个重要的研究领域,特别是基于视频的智能车辆监控系统中的运动车辆的检测和跟踪。提出一种自适应的背景估计方法来实时获得当前背景图像,从而分割出运动物体。为了准确地定位运动车辆的区域,采用差分图像投影和边缘投影相结合的方法来定位车体,同时利用双向加权联合图匹配方法对运动车辆区域进行跟踪,即将对运动车辆区域跟踪问题转化为搜索具有最大权的联合图的问题。该算法不仅能实时地定位和跟踪直道上运动的车辆,同时也能实时地定位和跟踪弯道上运动的车辆,从实验结果看,提出的背景更新算法简单,并且运动车辆区域的定位具有很好的鲁棒性,从统计的检测率和运行时间来看,该算法具有很好的检测效果,同时也能满足基于视频的智能交通监控系统的需要。
A vision-based moving object detection and tracking in video streams is an important research in computer vision, especially, the moving vehicles in ITS play an important role. The aim of motion detection is to get the changed region from the background image in video sequences, and it is also very important for target classification and tracking motion object. In this paper, a self-adaptive background subtraction method for vehicle segmentation was proposed. In order to locate vehicle accurately, we combined the projection of difference image with the projection of edge to locate vehicle. This proposed method could locate vehicle well. We formed an association graph between the regions from the previous frame and the regions from the current frame, so we modeled the tracking problem as a problem of finding maximal weight association graph. Very promising experimental results are provided using real-time video sequences, experimental results have confirmed that the proposed method is efficient and reliable, and its computer cost can also satisfy the traffic surveillance systems.
出处
《计算技术与自动化》
2004年第4期51-54,共4页
Computing Technology and Automation
关键词
实时
跟踪
背景估计
视频
图匹配
背景图像
计算机视觉
车辆
运动车
出运
motion detection
update background
object segmentation
region location
weight bipartite association graph
vehicle tracking
