近年来,视频序列图像中的运动目标检测在智能监控、视频压缩、自动导航、人机交互、虚拟现实等许多领域中的应用越来越广泛.论文提出了一种基于关键帧背景更新策略的运动目标检测算法,该算法采用视频序列中提取的关键帧作为背景,通过关键帧统计平均实现背景更新,结合矩阵像素差分和阈值判定来进行运动目标的检测.通过实验表明,本文提出的方法与典型的背景差检测相比,能够在一定程度上减少噪声的影响,提高运动目标检测的准确度.
Recent years, moving object detection of video frequency sequence image is more and more important in as areas such as intelligent monitoring,video compression, automatic navigation, man-machine interaction, virtual reality. In this paper, we propose a novel algorithm of moving object detection based on key frame background updating strategy. This algorithm uses key frame extracted from video as background and a- chieves background updating by key frames statistical average. Besides, it combines matrix pixel difference and threshold determination for moving object detection. The results show that the above method reduces the influence of noise and improves the accuracy of moving target detection.