Research of Target Segmentation Technology Based on Depth information

被引:0
作者
Lian, Duan [1 ]
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.
引用
收藏
页码:723 / 726
页数:4
相关论文
共 6 条
  • [1] Chan T, 2005, PROC CVPR IEEE, P1164
  • [2] Region growing: A new approach
    Hojjatoleslami, SA
    Kittler, J
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 1998, 7 (07) : 1079 - 1084
  • [3] Robust topology-adaptive snakes for image segmentation
    Ji, L
    Yan, H
    [J]. IMAGE AND VISION COMPUTING, 2002, 20 (02) : 147 - 164
  • [4] Korea poplar yuan XIA, 2006, J ELECT, V34, P2018
  • [5] Multiple motion segmentation with level sets
    Mansouri, AR
    Konrad, J
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2003, 12 (02) : 201 - 220
  • [6] Implicit and nonparametric shape reconstruction from unorganized data using a variational level set method
    Zhao, HK
    Osher, S
    Merriman, B
    Kang, M
    [J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 2000, 80 (03) : 295 - 314