基于视频图像序列的车行轨迹提取算法研究  

Algorithm of Motors Trajectory Extraction Based on Video Image Sequences

作　　者：侯晔星[1] 陈平[2] 刘宾[2] 

机构地区：[1]中国北方发动机研究所,山西大同037036 [2]中北大学电子测试技术国家重点实验室,太原030051

出　　处：《计算机测量与控制》2012年第8期2226-2229,共4页Computer Measurement &Control

基　　金：国家自然科学基金项目(61171179)

摘　　要：针对目前的交通监控以及驾驶员技能考核等领域的需求,提出了基于视频图像序列的车行轨迹提取算法;该算法是在研究路面图像特点的基础上,利用多目标优化理论,改进SIFT(Scale Invariant Feature Transform)算法中基于欧氏距离的特征匹配机制,提高SIFT特征点的匹配精度,从而提高车辆行驶轨迹提取精度;实验显示,该算法可以有效地提取车辆行驶轨迹,且提取精度为2cm,相对与常用的轨迹提取技术有了较大的进步。In allusion to the current traffic monitoring, driver skill examination and other requirements, the algorithm of motors trajecto- ry extraction based on video image sequences is proposed. First, based on researching the characteristic of road images, this algorithm has used multi--objective optimization technique to improve feature point matehing mechanism based on Euclidean distance, which is used in SIFT （Scale Invariant Feature Transform）. This can improve the precision of SIFT feature matching. Then improve the extracting precision of the actual track of vehicle. The experiment shows this algorithm can effectively extract the motors trajectory, and the preeision is 2em. This precision is better than the traditional method.

关 键 词：车行轨迹 多目标优化 SIFT特征 坐标变换 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]