基于颜色和边缘特征的球员目标分割方法  

Target Segmentation Method Based on Color and Edge Features

作　　者：王兵[1] 张卫国[1] 孙静茹[1] 张亮亮[1] 黄琨强 WANG Bing;ZHANG Weiguo;SUN Jingru;ZHANG Liangliang;HUANG Kunqiang(College of Computer and Communication Engineering,Zhenzhou University of Light Industry, Zhengzhou 450001, China)

机构地区：[1]郑州轻工业学院计算机与通信工程学院,郑州450001

出　　处：《湖北民族学院学报（自然科学版）》2017年第3期309-312,共4页Journal of Hubei Minzu University(Natural Science Edition)

基　　金：国家自然科学基金项目(81501547);2016年郑州轻工业学院研究生科技创新资助项目

摘　　要：为实现球员目标的准确分割,针对图像的颜色特征和球员的边缘特征提供的信息进行融合处理.首先对图像进行高斯滤波预处理,借助Matlab软件对图片进行了像素分析和筛选,并通过Prewitt算子进行边缘检测,以及Bresenham算法进行了直线扫描确定了边界线的起始,经过形态学运算将图片中直线段去除.并完成最终处理,将球员目标分割出来.其优点在于不受球场光照和阴影的影响,能够自动将观众等背景过滤,即使在复杂背景下也能较为准确的将目标分割出来.In order to achieve accurate segmentation of the target player,we conduct fusion processing based on the information provided by the color features of the image and the edge features of the player.Firstly,the image is pre-processed by Gaussian filtering,and the pixels are analyzed and screened by Matlab software.The edge detection is carried out by Prewitt operator and the Bresenham algorithm is used to determine the start of the boundary line. After morphological operation,the line is removed in the picture.After the final processing,the target player is segmented.The advantage of this method is that it is not affected by the lighting and shadows of the soccer field and it can automatically filter the background of the spectators and accurately segment the target even in the complex background.

关 键 词：融合 PREWITT算子 BRESENHAM算法 目标提取 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]