摘要
借助颜色加权模糊直方图提取运动目标,以降低动态变化背景造成的干扰。计算任意位置所对应邻域方差,将其与高斯函数相结合,构造出一种灰度空间位置相关的权函数;统计彩色图像的颜色加权直方图,利用模糊C均值聚类方法对颜色直方图聚类,以所得隶属度与颜色直方图之积作为模糊直方图;运用颜色模糊直方图相交叉的背景减除法,对运动目标进行提取。针对两个视频序列的测试结果表明,所给算法可降低因光照强度变化而产生的背景移动假象对运动目标提取造成的干扰,能从复杂场景视频序列中提取出目标。
A method based on weighted color historgram is proposed to extracte moving objects,so as to reduce the interference caused by the dynamic background.Calculate the variance of the neighborhood of any position and combine it with the Gauss function to construct a weight function of gray space position correlation.The weighted color histogram of color image is statistically analyzed,and the fuzzy C-means clustering method is used to cluster the color histogram.Multiplie the color histogram with the membership degree obtained in this process,and regard their product as a fuzzy histogram.By using the background subtraction of fuzzy color histogram intersection,the moving target can be extracted.Test results for two video sequences show that,the proposed algorithm can reduce the interference from the background motion artifacts caused by the change of illumination intensity,anc extract the target from a complex scene video sequence.
出处
《西安邮电大学学报》
2017年第5期22-27,共6页
Journal of Xi’an University of Posts and Telecommunications
基金
国家自然科学基金重点资助项目(61136002)
陕西省自然科学基金资助项目(2014JM8331
2014JQ5183
2014JM8307)
陕西省教育厅科学研究计划资助项目(2015JK1654)
关键词
运动目标提取
加权直方图
模糊C均值聚类
背景减除法
moving object extraction, weighted histogram, fuzzy C-clustering, background subtractio
