基于图像配准的动态场景运动目标检测算法  

Study on Moving Object Detection Algorithm Based on Different Color Space

作　　者：丁莹[1,2] 范静涛[2] 杨华民[2] 姜会林[1] 

机构地区：[1]长春理工大学光电测控与光信息传输技术教育部重点实验室,长春130022 [2]长春理工大学计算机科学技术学院,长春130022

出　　处：《长春理工大学学报（自然科学版）》2013年第1期4-9,共6页Journal of Changchun University of Science and Technology(Natural Science Edition)

基　　金：国家科技支撑计划项目(2009BAE69B02)

摘　　要：针对摄像机运动的动态场景下运动目标的检测问题,提出了基于Harris角点方根-算术均值距离配准的动态场景运动目标检测算法。首先将当前帧图像与前一帧图像进行配准,获取图像的全局运动参数;利用求得的运动参数对当前图像进行运动补偿;然后,将其与存储的前两帧图像进行帧差法,以获得运动目标的轮廓信息;以该运动目标区域为掩模,检测并定位该运动目标。实验结果表明,此算法能够较好的处理摄像机运动等动态场景情况下的运动目标定位问题,为运动目标的跟踪和识别奠定基础。For moving object detection in dynamic scene, the paper presents a moving object detection algorithm of dynamic scenes based on Harris comer points＇ SAM. Firstly, registers the current frame image with the previous image to catch the global motion parameters; compensates image motion by using of the motion parameters; and then takes frame differencing method with the first two images, to get the outline of moving object; regards moving region as mask, and detects and locates the moving target.The experimental results show that this algorithm can deal with positioning of moving targets of dynamic scenes, such as camera motion, etc. which lay the foundation for moving target tracking and identification.

关 键 词：运动目标检测 动态场景 图像配准 帧差法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]