摘要: 给出了一种实用的在复杂背景下检测运动目标的方法。提出了对序列差图像进行累积以突出目标和消除干扰的策略,论述了累积图像的性质,解决了自动阈值选取的问题;提出了周期和非周期性运动目标的区分策略,给出了目标的定位方法。尤其对图像噪声、背景干扰和不同图像的特点等给出了一定的分析、描述和针对性解决策略。该文方法可以快速实现并已经取得了很好的应用效果。
关键词:
目标检测,
差图像,
图像噪声,
二值化
Abstract: This paper introduces a new practical method for detecting moving targets under complex background.The strategy of target enhancement and noise reduction is proposed;the characters and the threshold selection of difference image are analyzed;the method to exclude targets periodically moving and locate the really target is given.Especially,this paper pays more attention on analysis and solutions of image noise,disturbance from scene,and properties of different type images.The method proposed in this paper has been successfully applied in an autonomous control system.
中图分类号:
任明武,孙涵. 复杂背景下一种实用的运动目标检测方法[J]. , 2005, 31(20): 42-.
REN Mingwu,SUN Han. A Practical Method for Moving Target Detection Under Complex Background[J]. , 2005, 31(20): 42-.