摘要
提出了一种新的基于HSV颜色空间的阴影检测和误判检测的自适应背景模型运动目标检测算法,并将其应用于运动物体的分割。该算法较好地解决了背景模型的提取、更新、背景扰动、外界光照变化等问题。实验结果表明了该算法的实时性、可靠性和准确性较好。
In the paper, we propose an adaptive HSV coh）r background model with shadow and false detection to segment moving objects. The algorithm effectively deals with the problems of the abstraction and update of background, background disturbance, illumination changes etc. Experiments show that the method is reliable, and can be used in relevant real-time applications.
出处
《微计算机信息》
2010年第5期199-200,196,共3页
Control & Automation
关键词
混合高斯模型
目标检测
阴影消除
误判检测
mixture Gaussian model
Object detection
Shadow elimination
false detection
