基于OpenCV的运动目标检测与跟踪  

Detection and tracking of moving objects based on OpenCV

作　　者：尹俊超[1] 刘直芳[1,2] 

机构地区：[1]四川大学计算机学院,四川成都610064 [2]四川大学视觉合成图形图像技术国防重点学科实验室,四川成都610064

出　　处：《计算机工程与设计》2011年第8期2817-2820,共4页Computer Engineering and Design

基　　金：国家863高技术研究发展计划基金项目(2007AA01Z328;2009AA01Z332);国家自然科学基金项目(60736046)

摘　　要：基于OpenCV开源平台开发了一种多运动目标检测和跟踪的自动化智能方案。针对多个运动目标在复杂场景中的情况,无法根据背景差和帧间差的方法来确定目标是否首次出现,根据新目标期望出现的位置范围和轮廓面积大小采用筛选法来判断目标的性质。利用CAMShift跟踪算法提取每个目标的颜色特征信息,实现对多个运动目标的跟踪,最后将运动目标的轮廓和运动轨迹描述出来。实验结果表明,在目标颜色特征明显的情况下文中方法具有很好的鲁棒性和精确性。Based on OpenCV open source platform, an automated and intelligent program for more moving targets＇ detection and tracking is developed. For multiple moving targets in complex scenes of the situation, can＇ t be according to background subtraction and the frame difference method to determine whether the target the first time appears, by preparation, according to the area where a new target expected to appear to determine whether the target is new. CAMShift tracking algorithm can be adapted to extract the color feature information for each target to achieve the tracking of multiple moving targets. Finally, the outline and the trajectory of moving objects are described. Experimental results show that the method has good robustness and accuracy if the targets have obvious color features.

关 键 词：OPENCV 检测 跟踪 帧间差 背景差 背景重构 CAMSHIFT 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]