视频序列中运动目标自动提取的研究

Research on Automatic Segmentation of Moving Object in Video Sequences

本文提出了一种从彩色视频序列中,有效分割运动目标的算法。首先将当前帧图像和背景参考图像在YUV彩色空间中进行距离差分得到距离差分图像,然后根据差分图像直方图的单峰聚集特性,提出了基于直方图的自适应聚类分割算法;对分割后的二值图像采用图像形态学方法去除无用的噪声斑点,并根据得到运动模板,提出了背景参考图像的更新策略。实验结果表明这是一种简单、有效的运动目标提取方法。

This paper presents an effective segmentation method for moving objects in color video sequences. The difference image of color distance between current image and the reference background image in YUV color space is first obtained. According to the mono-modal feature of histogram of the difference image, we propose an adaptive clustering segmentation method based on histogram. The image morphology filtering is employed to remove the flecks of noise existed in the segmented binary image. Finally, an updating scheme for background image is introduced to follow the variation of illumination conditions and changes in environmental conditions. Experimental results show that the proposed method is simple and effective in extracting moving objects from video sequences.