Saliency detection for panoramic landscape images of outdoor scenes

被引:8
作者
Han, Byeong-Ju [1 ]
Sim, Jae-Young [1 ]
机构
[1] Ulsan Natl Inst Sci & Technol, Sch Elect & Comp Engn, Ulsan, South Korea
基金
新加坡国家研究基金会;
关键词
Saliency detection; Panoramic image; Wide fields of view; Background estimation; Saliency refinement; VISUAL-ATTENTION; REGION DETECTION; MODEL;
D O I
10.1016/j.jvcir.2017.08.003
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Saliency detection has been researched for conventional images with standard aspect ratios, however, it is a challenging problem for panoramic images with wide fields of view. In this paper, we propose a saliency detection algorithm for panoramic landscape images of outdoor scenes. We observe that a typical panoramic image includes several homogeneous background regions yielding horizontally elongated distributions, as well as multiple foreground objects with arbitrary locations. We first estimate the background of panoramic images by selecting homogeneous superpixels using geodesic similarity and analyzing their spatial distributions. Then we iteratively refine an initial saliency map derived from background estimation by computing the feature contrast only within local surrounding area whose range and shape are changed adaptively. Experimental results demonstrate that the proposed algorithm detects multiple salient objects faithfully while suppressing the background successfully, and it yields a significantly better performance of panorama saliency detection compared with the recent state-of-the-art techniques. (c) 2017 Elsevier Inc. All rights reserved.
引用
收藏
页码:27 / 37
页数:11
相关论文
共 38 条
  • [1] SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
    Achanta, Radhakrishna
    Shaji, Appu
    Smith, Kevin
    Lucchi, Aurelien
    Fua, Pascal
    Suesstrunk, Sabine
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (11) : 2274 - 2281
  • [2] SALIENCY DETECTION FOR CONTENT-AWARE IMAGE RESIZING
    Achanta, Radhakrishna
    Suesstrunk, Sabine
    [J]. 2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6, 2009, : 1005 - 1008
  • [3] Achanta R, 2009, PROC CVPR IEEE, P1597, DOI 10.1109/CVPRW.2009.5206596
  • [4] [Anonymous], 2007, COMPUTER VISION PATT, DOI DOI 10.1109/CVPR.2007.383017
  • [5] [Anonymous], 2007, Computer Vision and Pattern Recognition (CVPR), IEEE Conference on
  • [6] A site entropy rate and degree centrality based algorithm for image co-segmentation
    Chakraborty, Souradeep
    Mitra, Pabitra
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2015, 33 : 20 - 30
  • [7] Sketch2Photo: Internet Image Montage
    Chen, Tao
    Cheng, Ming-Ming
    Tan, Ping
    Shamir, Ariel
    Hu, Shi-Min
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2009, 28 (05): : 1 - 10
  • [8] Efficient Salient Region Detection with Soft Image Abstraction
    Cheng, Ming-Ming
    Warrell, Jonathan
    Lin, Wen-Yan
    Zheng, Shuai
    Vineet, Vibhav
    Crook, Nigel
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2013, : 1529 - 1536
  • [9] Stretchability-aware block scaling for image retargeting
    Du, Huan
    Liu, Zhi
    Jiang, Jianliang
    Shen, Liquan
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2013, 24 (04) : 499 - 508
  • [10] Salient region detection through sparse reconstruction and graph-based ranking
    Fareed, Mian Muhammad Sadiq
    Ahmed, Gulnaz
    Chun, Qi
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2015, 32 : 144 - 155