用于监控视频的滞留与搬移物体的检测算法  

Detection and Classification Algorithm for Abandoned and Moved Objects Used in Surveillance Video

作　　者：夏应高[1] 朱秀昌[1] 

机构地区：[1]南京邮电大学江苏省图像处理与图像通信重点实验室,江苏南京210003

出　　处：《电视技术》2008年第12期86-88,91,共4页Video Engineering

摘　　要：提出了一种新的滞留与搬移物体的检测分类算法。该算法利用背景差法获得前景图像,然后进行二值化和形态学处理,再和背景帧进行比较来对滞留和搬移物体进行检测和分类。实验结果表明该检测算法具有较高的正确率和鲁棒性。A new detection and classification algorithm for abandoned and moved objects is proposed in this paper. This new algorithm uses the background subtraction method to get the foreground image, and then gets the binary image using threshold value and makes the morphology, processing. The algorithm compares the binary image with the background frame to classify the objects into abandoned and moved. The experiment results show that the algorithm has high correct rate and robustness.

关 键 词：智能视频 滞留与搬移 背景差法 形态学处理 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]