视频监视中运动目标检测与识别方法  

Moving Object Detection and Recognition Method for Video Monitoring System

作　　者：李庆忠[1] 陈显华[1] 王立红[1] 

机构地区：[1]中国海洋大学机电工程系,青岛266071

出　　处：《计算机工程》2004年第16期143-145,共3页Computer Engineering

摘　　要：针对户外监视应用背景,提出了彩色图像差值模型、自适应阈值分割算法、图像形态学噪声滤除方法,实现了户外场景中运动目标的有效检测;对分割后的目标,提取不变矩特征,然后利用人工神经网络实现了运动目标的快速识别。实验结果验证了上述方法的有效性。This paper first presents an efficient moving object detection method for outdoor surveillance environments. The presented method consists of a color image difference model, an adaptive thresholding method, and an image morphology filtering method. Moreover, by extracting shape invariant moment characteristics of object region, this paper also presents a BP neural network based object recognition method. Experimental results demonstrate that the proposed approach can detect and identify moving objects effectively for outdoor surveillance environments.

关 键 词：运动目标检测 视频监视系统 图像分割 人工神经网络 图像形态学 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]