Research of Target Segmentation Technology Based on Depth information
被引:0
作者:
Lian, Duan
论文数: 0引用数: 0
h-index: 0
机构:
Changchun Univ Sci & Technol, Sch Elect & Informat Engn, Changchun 130022, Peoples R ChinaChangchun Univ Sci & Technol, Sch Elect & Informat Engn, Changchun 130022, Peoples R China
Lian, Duan
[1
]
Yan, Piao
论文数: 0引用数: 0
h-index: 0
机构:
Changchun Univ Sci & Technol, Sch Elect & Informat Engn, Changchun 130022, Peoples R ChinaChangchun Univ Sci & Technol, Sch Elect & Informat Engn, Changchun 130022, Peoples R China
Yan, Piao
[1
]
机构:
[1] Changchun Univ Sci & Technol, Sch Elect & Informat Engn, Changchun 130022, Peoples R China
来源:
2013 2ND INTERNATIONAL SYMPOSIUM ON INSTRUMENTATION AND MEASUREMENT, SENSOR NETWORK AND AUTOMATION (IMSNA)
|
2013年
关键词:
Statistical Region Integration;
Depth Information;
Graph Cuts;
D O I:
暂无
中图分类号:
TP [自动化技术、计算机技术];
学科分类号:
0812 ;
摘要:
For segmentation algorithm widespread over-segmentation problem, design a combination of depth information and color information approach. Firstly, the image depth information combined statistical area in which the fill color on the basis of information obtained initial segmentation results, then combine Graph Cuts algorithm to over-segmentation part, and finally get the exact target. Through a variety of algorithms can be combined advanced segmentation results. Simulation results show that the new algorithm can effectively inhibit the design over-segmentation and under-segmentation, more precise target.