融合HSV空间与形态学的救生衣图像分割  

LIFE JACKET IMAGE SEGMENTATION FUSING HSV SPACE AND MORPHOLOGY

作　　者：谭晓波[1] 殷苌茗[1] 周书仁[1] 

机构地区：[1]长沙理工大学计算机与通信工程学院,湖南长沙410014

出　　处：《计算机应用与软件》2016年第1期198-202,共5页Computer Applications and Software

基　　金：湖南省自然科学基金项目(12JJ6057);湖南省教育厅科研项目(13B132);长沙市科技计划项目(K1203015-11)

摘　　要：针对轮船渡口拍摄图像背景复杂、噪声大、模糊的特点,提出一种融合HSV颜色空间信息和数学形态学处理的图像分割方法,并进行背景差分提取前景,消除错误的背景分割。首先提取目标物体的HSV颜色特征值,然后利用得到的特征值标记ROI区域,对该含有标记信息的二值图像进行数学形态学处理得到连通区域图,通过连通区域外轮廓找出最外矩形边界,最后利用背景差分消除背景干扰。将该方法应用于轮渡安全中救生衣的检测,实验结果表明,能快速有效地实现救生衣图像分割,并对分割区域进行计数。As to the characteristics of complex background, big noise and vague in pictures taken at ship ferry, in this paper we present an image segmentation method which combines HSV colour space information with mathematical morphology processing, and conduct background subtraction to extract foregrounds and eliminate wrong background segmentation. The method first extracts HSV colour feature values of target object, then uses the derived feature value to mark ROI areas, then operates the mathematical morphology on binary images containing tag information to get the connected areas graph, and finds the outside rectangle boundary through the contours of connected areas, finally it uses background subtraction to eliminate background interference. Applying the method to the detection of life jackets used for ferry safety, experimental results show that it can quickly and effectively achieve the segmentation of life jacket image, and counts the number of segmenting areas.

关 键 词：HSV颜色空间 数学形态学 背景差分 图像分割 特征提取 ROI区域 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]