基于运动向量模型的车辆检测  

Moving Vehicle Detection Based on Motion Vector Model

作　　者：徐煜[1] 方向忠[1] 

机构地区：[1]上海交通大学图像通信与信息处理研究所电子工程系上海数字媒体处理与传输重点实验室,上海200240

出　　处：《电视技术》2007年第9期74-76,86,共4页Video Engineering

基　　金：国家"863"计划项目(2006AA01Z124)

摘　　要：提出一种算法,它针对动态背景和运动车辆运动向量的各自特征分别进行相应建模,再利用图像的帧内信息修正模型参数,并使用贝叶斯准则检测出运动车辆,实验结果表明,此方法具有更高的车辆检测准确率。This paper presents the algorithm for moving vehicle detection in image sequences of traffic scenes. By investigating the distinction between the motion vectors of the dynamic background and those of the moving vehicles, motion models are set up respectively. Then, the intra-frame information is used to modify the motion model. Finally, Bayesian decision rule is implemented to detect vehicle from dynamic background. Experimental results show that the proposed method can detect moving vehicle more accurately and robustly in complex and dynamic scenes.

关 键 词：车辆检测 运动向量模型 高斯模型 贝叶斯判决 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]