| 基于运动向量模型的车辆检测 |
| |
| 引用本文： | 徐煜,方向忠.基于运动向量模型的车辆检测[J].电视技术,2007,31(9):74-76,86. |
| |
| 作者姓名： | 徐煜 方向忠 |
| |
| 作者单位： | 1. 上海交通大学,图像通信与信息处理研究所,电子工程系
2. 上海数字媒体处理与传输重点实验室,上海,200240 |
| |
| 基金项目： | 国家高技术研究发展计划(863计划) |
| |
| 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.
|
| 关 键 词： | 车辆检测 运动向量模型 高斯模型 贝叶斯判决 |
| 文章编号： | 1002-8692（2007）09-0074-03 |
| 修稿时间： | 2007-07-12 |
Moving Vehicle Detection Based on Motion Vector Model |
| |
| XU Yu,FANG Xiang-zhong.Moving Vehicle Detection Based on Motion Vector Model[J].Tv Engineering,2007,31(9):74-76,86. |
| |
| Authors: | XU Yu FANG Xiang-zhong |
| |
| Affiliation: | Institute of Image Communication and Information Processing, Department of Electronic Engineering; Shanghai Key Laboratory of Digital Media Processing and Transmissions, Shanghai Jiaotong University, Shanghai 200240, China |
| |
| Abstract: | 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. |
| |
| Keywords: | moving vehicle detection moving vector model Gaussian model Bayesian decision rule |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
