一种俯视行人的多目标检测和跟踪方法  

Zenithal Pedestrian Detection and Tracking

作　　者：唐春晖[1,2] 陈启军[1] 

机构地区：[1]同济大学电信学院,上海310027 [2]上海理工大学光电学院,上海200093

出　　处：《系统仿真学报》2013年第10期2464-2467,共4页Journal of System Simulation

基　　金：国家自然科学基金(91120308);上海市教育委员会重点学科建设项目资助(J50505);上海市科技人才计划项目(11XD1404800)

摘　　要：提出了一种针对俯视客流计数的多目标自动检测和跟踪方法。该方法主要包括四个组成部分:运动检测、目标表示与识别、目标跟踪建模、目标跟踪。即首先通过视频帧间差法粗略检测出一帧图像中成片运动或变化的区域,在变化区域里遍历搜索目标;视觉目标表示为外形对称、外观具有某种形状结构、颜色均匀等一系列弱分类特征串联组成的形式,可以快速检测判别俯视行人的头部;再对检测到目标重新建模以便后续的跟踪;最后利用连续自适应的均值移位算法跟踪检测到的多个目标。检测与跟踪并行运行,跟踪可以验证检测到的目标。实验证明,该方法是有效的。A method of automatic multi-target detection and tracking with respect to zenithal pedestrian counting was put forward. There are mainly four parts. motion detection, object modeling, object detection and tracking. First the motion area is segmented using frame difference. Then the pedestrian head can be quickly detected using a series of simple cascaded characteristic in the area, such as the symmetry or asymmetry of a head, some shape of the appearance and the uniform color of that. After that, a suitable object model is set up to keep track of location and otherproperties. At last these targets can be tracking using the continuous adaptive mean shift tracking algorithm. Object detection and tracking run simultaneously and the tracking can verify the detection. Experiments show that the method is effective.

关 键 词：检测 跟踪 多目标 俯视图 连续自适应均值移位 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]