Automatic RGBD Object Segmentation Based on MSRM Framework Integrating Depth Value

首页 > 成果 > 详情

认领

导出

Link by 万方学术期刊

反馈

作者信息关键词期刊信息基础信息归属信息摘要

成果类型：

期刊论文

作者：

Li, Guoqing;Zhang, Guoping（张国平）;Qin, Chanchan;Lu, Anqin

通讯作者：

Chanchan Qin

作者机构：

[Zhang, Guoping; Li, Guoqing] Cent China Normal Univ, Coll Phys Sci & Technol, 152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.

[Zhang, Guoping; Li, Guoqing] Cent China Normal Univ, Key Lab Quark & Lepton Phys MOE, 152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.

[Qin, Chanchan; Lu, Anqin] Guizhou Normal Univ, Sch Big Data & Comp Sci, Guiyang 550025, Guizhou, Peoples R China.

[Qin, Chanchan; Lu, Anqin] Guizhou Normal Univ, Ctr RFID & WSN Engn, Dept Educ, Guiyang 550025, Guizhou, Peoples R China.

通讯机构：

[Chanchan Qin] S

School of Big Data and Computer Science, Guizhou Normal University, The University Town, Guian New Area, Guiyang, Guizhou 550025, China<&wdkj&>Center for RFID and WSN Engineering, Department of Education, Guizhou Normal University, The University Town, Guian New Area, Guiyang, Guizhou 550025, China

语种：

英文

关键词：

Image segmentation;depth value;saliency estimation;region merging;maximal geometry weighted similarity

期刊：

International Journal on Artificial Intelligence Tools

ISSN：

0218-2130

年：

2020

卷：

期：

07n08

页码：

2040009

DOI：

10.1142/S0218213020400096

基金类别：

Natural Science Foundation of Hubei ProvinceNatural Science Foundation of Hubei Province [2017CFB591]; Science and Technology Foundation of Guizhou Province of China [[2015]2120]; Doctoral Scientific Research Foundation of Guizhou Normal University

机构署名：

本校为第一机构

院系归属：

物理科学与技术学院

摘要：

In this paper, an automatic RGBD object segmentation method is described. The method integrates depth feature with the cues from RGB images and then uses maximal similarity based region merging (MSRM) method to obtain the segmentation results. Firstly, the depth information is fused to the simple linear iterative clustering (SLIC) method so as to produce superpixels whose boundaries are well adhered to the edges of the natural image. Meanwhile, the depth prior is also incorporated into the saliency estimation, which helps a more accurate localization of representative object and background see...

反馈

产权有误：本人成果被他人认领

数据有误：数据基本信息有误

归属有误：成果的院系归属、机构署名归属有误

其他原因：

验证码：

看不清楚，换一个

确定

取消

成果认领

标题：

用户	作者	通讯作者	--
	请选择	请选择	--

确定

取消

Automatic RGBD Object Segmentation Based on MSRM Framework Integrating Depth Value

反馈

成果认领

提示

该栏目需要登录且有访问权限才可以访问