摘要
局部凸连接生长算法(LCCP)存在超体素跨越物体边界,未能利用区域隐含凹凸信息的缺陷,为了改进以上缺陷导致的分割精确度低、物体粘连的问题,提出了结合连通域分割的改进算法。首先采用深度自适应超像素分割法(DASP)根据深度信息和法向量角度将图片划分为超像素;其次根据超像素的法向量夹角判定邻接超像素的凹凸性,合并所有凸连接超像素形成初步结果;最后使用基于超像素的距离变换以及分水岭生长分割方法,把面积较大的凹连通域,快速分割成多个凸区域。在IC-BIN数据集进行分割验证,结果表明平均分割精度(AP)相比于LCCP和约束平面切割法(CPC)分别提升25%和35%,显著改善了欠分割问题。
The local convex connected Patches algorithm(LCCP)suffers from the defects of super voxels crossing object boundaries and failing to utilize the regionally implicit concave-convex information.In order to improve the problems of low segmentation accuracy and object adhesion caused by the above defects,an improved algorithm combining connected domain segmentation is proposed.Firstly,the depth-adaptive superpixel segmentation(DASP)method is used to divide the image into superpixels based on depth information and normal vector angle.Secondly,the concave-convexity of neighboring superpixels is determined based on the normal vector angle of superpixels,and all convex connected superpixels are combined to form the preliminary result.Finally,the distance transformation and the watershed growth segmentation method based on superpixels are used to quickly segment the concave connected domain with large area into multiple convexregions.The segmentation is validated on the IC-BIN dataset,and the results show that the average segmentation accuracy(AP)is improved by 25%and 35%compared to LCCP and constrained plane cut(CPC),respectively,which significantly improves the under-segmentation problem.
作者
王瑞丰
朱铮涛
冯端奇
Wang Ruifeng;Zhu Zhengtao;Feng Duanqi(School of Mechanical and Electrical Engineering,Guangdong University of Technology,Guangzhou 511400,China)
出处
《电子测量技术》
北大核心
2022年第3期118-124,共7页
Electronic Measurement Technology
基金
广东省科技计划项目(2020A0505100012)资助。
关键词
超像素
凹凸性
距离变换
分水岭
图像分割
superpixel
convexity
distance transform
watershed
image segmentation
