基于背景差分法的运动目标分割

Moving Object Segmentation Based on Background Subtraction

运动目标分割在基于视频的运动目标检测与识别研究中发挥着重要作用。以图像差分法为基础,实现了一种复杂背景下快速分割运动目标的方法。通过中值滤波对原始图像进行预处理;运用改进的Surendra算法快速提取并更新背景图像;利用数学形态学运算对差分二值图像进行处理,进行运动区域的初始检测;将RGB图像转换到HSI域中进行适当的阴影去除,完成运动目标分割。实验结果表明该方法能够较为有效地分割出感兴趣区域(ROI)内的运动目标。

Moving object segmentation plays an important role in video-based moving target detection and recognition,this paper achieves a fast segmentation method of moving targets in complex background.The original image is preprocessed by the median filtering.The improved surendra algorithm is used to extract and update the background image rapidly.The mathematical morphological operations are used to process the differential binary image to finish the initial segmentation of the motion region.The RGB image is converted to the HSI domain to remove the shadow of the object to complete the moving object segmentation.Experimental results show that the method can segment the moving object within the region of interest more effectively.