摘要
提出一种能够在视频监控系统中检测操作台遗留物的检测方法,并在实际的安防系统中应用本算法。首先通过混合高斯建模(GMM)算法检测出前景目标,然后使用形态学滤波方法对前景目标进行筛选,最后判断前景目标是否为遗留物。经过实验验证,使用本算法的遗留物检测系统,具有较高的检测正确率,并且本系统对复杂环境具有较好的适应性,实验验证本文算法的可行性和有效性。
Presents a method to detect the legacy of the operating table in the video monitoring system, and realizes the algorithm in the actual secu- rity system. Firstly, uses Gaussians Mixture Model （GMM） to detect the foreground object, and then uses the morphological filtering method to screen the foreground object. After experimental verification, legacy detection system using this algorithm has higher detection accuracy, and the system has good adaptability to complex environment, to verify the feasibility and effectiveness of the algorithm.
关键词
遗留物检测
混合高斯建模
图像形态学
Abandoned Object Detection
Gaussians Mixture Model
Image Morphology
