Video object segmentation with shape cue based on spatiotemporal superpixel neighbourhood

被引:13
作者
Tian, Zhiqiang [1 ]
Zheng, Nanning [1 ]
Xue, Jianru [1 ]
Lan, Xuguang [1 ]
Li, Ce [1 ]
Zhou, Gang [1 ]
机构
[1] Xi An Jiao Tong Univ, Inst Artificial Intelligence & Robot, Xian 710049, Peoples R China
关键词
IMAGE SEGMENTATION; GRAPH CUTS;
D O I
10.1049/iet-cvi.2012.0189
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this study, the authors present a method to extract moving objects in image sequences. The proposed approach is based on a graph cuts algorithm defined on a spatiotemporal superpixel neighbourhood. Presegmented superpixels are partitioned into foreground and background while preserving temporal and spatial coherence. It achieves this goal by three steps. First, instead of operating at pixel level, the superpixels are advocated as basic units of the authors segmentation scheme. Second, within the graph cuts framework, two superpixel-based data terms and two superpixel-based smoothness terms are proposed to solve segmentation problem. Finally, the proposed method yields the segmentation of all the superpixels within video volume by the graph cuts algorithm. To illustrate the advantages of this approach, the quantitative and qualitative results are compared with other state-of-the-art methods. The experimental results show that the proposed method gives better performance of segmentation with respect to these methods. © The Institution of Engineering and Technology 2014.
引用
收藏
页码:16 / 25
页数:10
相关论文
共 50 条
  • [21] A predefined object tracking method for video segmentation
    Kim, D
    Kim, M
    Choi, JG
    Ho, YS
    ELECTRONIC IMAGING AND MULTIMEDIA SYSTEMS II, 1998, 3561 : 43 - 51
  • [22] Learning Based Superpixel Merging Model for Image Segmentation
    Huang, Jin-Yu
    Ding, Jian-Jiun
    Huang, Pei-Chi
    29TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2021), 2021, : 661 - 665
  • [23] Superpixel Segmentation Based on Spatially Constrained Subspace Clustering
    Li, Hua
    Jia, Yuheng
    Cong, Runmin
    Wu, Wenhui
    Kwong, Sam Tak Wu
    Chen, Chuanbo
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2021, 17 (11) : 7501 - 7512
  • [24] Self-Teaching Video Object Segmentation
    Zhou, Chuanwei
    Xu, Chunyan
    Cui, Zhen
    Zhang, Tong
    Yang, Jian
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (04) : 1623 - 1637
  • [25] Learning Based SLIC Superpixel Generation and Image Segmentation
    Chang, Chieh-Sheng
    Ding, Jian-Jiun
    Lin, Heng-Sheng
    2019 INTERNATIONAL SYMPOSIUM ON INTELLIGENT SIGNAL PROCESSING AND COMMUNICATION SYSTEMS (ISPACS), 2019,
  • [26] The image segmentation based on optimized spatial feature of superpixel
    Tian, Xiaolin
    Jiao, Licheng
    Yi, Long
    Guo, Kaiwu
    Zhang, Xiaohua
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2015, 26 : 146 - 160
  • [27] PFS: Particle-Filter-Based Superpixel Segmentation
    Xu, Li
    Luo, Bing
    Pei, Zheng
    Qin, Keyun
    SYMMETRY-BASEL, 2018, 10 (05):
  • [28] Research on the Grabcut Image Segmentation Method Based on Superpixel
    Liu, Yang
    Zhou, Ningning
    Huang, Guofang
    2017 12TH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS AND KNOWLEDGE ENGINEERING (IEEE ISKE), 2017,
  • [29] Weakly Supervised Foreground Segmentation Based on Superpixel Grouping
    Yu, Wangsheng
    Hou, Zhiqiang
    Wang, Peng
    Qin, Xianxiang
    Wang, Liguang
    Li, Huanyu
    IEEE ACCESS, 2018, 6 : 12269 - 12279
  • [30] Superpixel-based segmentation algorithm for mature citrus
    Yang, Qinghua
    Chen, Yiqin
    Xun, Yi
    Bao, Guanjun
    INTERNATIONAL JOURNAL OF AGRICULTURAL AND BIOLOGICAL ENGINEERING, 2020, 13 (04) : 166 - 171