Saliency-based superpixels

被引:13
|
作者
Xu, Linfeng [1 ]
Zeng, Liaoyuan [1 ]
Wang, Zhengning [1 ]
机构
[1] Univ Elect Sci & Technol China, Sch Elect Engn, Chengdu 611731, Sichuan, Peoples R China
基金
中国博士后科学基金; 国家高技术研究发展计划(863计划);
关键词
Visual attention; Saliency model; Superpixel; Merging strategy; VISUAL-ATTENTION; MODEL; SEGMENTATION; EXTRACTION; TRACKING;
D O I
10.1007/s11760-013-0520-8
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Superpixels provide an over-segmentation representation of a natural image. However, they lack information of the entire object. In this paper, we propose a method to obtain superpixels through a merging strategy based on the bottom-up saliency values of superpixels. The proposed method aims to obtain meaningful superpixels, i.e., make the objects as complete as possible. The proposed method creates an over-segmented representation of an image. The saliency value of each superpixel is calculated through a biologically plausible saliency model in a way of statistical theory. Two adjacent superpixels are merged if the merged superpixel is more salient than the unmerged ones. The merging process is performed in an iterative way. Experimental evaluation on test images shows that the obtained saliency-based superpixels can extract the salient objects more effectively than the existing methods.
引用
收藏
页码:181 / 190
页数:10
相关论文
共 50 条
  • [41] Saliency-based framework for facial expression recognition
    Khan, Rizwan Ahmed
    Meyer, Alexandre
    Konik, Hubert
    Bouakaz, Saida
    FRONTIERS OF COMPUTER SCIENCE, 2019, 13 (01) : 183 - 198
  • [42] Saliency-Based Compressive Sampling for Image Signals
    Yu, Ying
    Wang, Bin
    Zhang, Liming
    IEEE SIGNAL PROCESSING LETTERS, 2010, 17 (11) : 973 - 976
  • [43] Saliency-based Rhythmic Coordination of Perceptual Predictions
    Huang, Qiaoli
    Luo, Huan
    JOURNAL OF COGNITIVE NEUROSCIENCE, 2020, 32 (02) : 201 - 211
  • [44] Saliency-based image quality assessment criterion
    Ma, Qi
    Zhang, Liming
    ADVANCED INTELLIGENT COMPUTING THEORIES AND APPLICATIONS, PROCEEDINGS: WITH ASPECTS OF THEORETICAL AND METHODOLOGICAL ISSUES, 2008, 5226 : 1124 - +
  • [45] Saliency-based image correction for colorblind patients
    Jinjiang Li
    Xiaomei Feng
    Hui Fan
    ComputationalVisualMedia, 2020, 6 (02) : 169 - 189
  • [46] A SALIENCY-BASED METHOD FOR SAR TARGET DETECTION
    Li, Haixiang
    Yu, Xuelian
    Wang, Xuegang
    IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 2837 - 2840
  • [47] Action recognition by saliency-based dense sampling
    Xu, Zengmin
    Hu, Ruimin
    Chen, Jun
    Chen, Chen
    Chen, Huafeng
    Li, Hongyang
    Sun, Qingquan
    NEUROCOMPUTING, 2017, 236 : 82 - 92
  • [48] Saliency detection based on superpixels clustering and stereo disparity
    Gao Shan-shan
    Chi Jing
    Li Li
    Zou Ji-biao
    Zhang Cai-ming
    APPLIED MATHEMATICS-A JOURNAL OF CHINESE UNIVERSITIES SERIES B, 2016, 31 (01) : 68 - 80
  • [49] Saliency detection based on superpixels clustering and stereo disparity
    GAO Shan-shan
    CHI Jing
    LI Li
    ZOU Ji-biao
    ZHANG Cai-ming
    AppliedMathematics:AJournalofChineseUniversities, 2016, 31 (01) : 68 - 80
  • [50] Saliency detection based on superpixels clustering and stereo disparity
    Shan-shan Gao
    Jing Chi
    Li Li
    Ji-biao Zou
    Cai-ming Zhang
    Applied Mathematics-A Journal of Chinese Universities, 2016, 31 : 68 - 80