Detecting salient cues through illumination-invariant color ratios

被引:0
|
作者
Todt, E [1 ]
Torras, C [1 ]
机构
[1] UPC, CSIC, Inst Robot & Informat Ind, E-08028 Barcelona, Spain
关键词
visual landmarks; color constancy; visual saliency; visual robot navigation;
D O I
10.1016/S0921-8890(04)00089-2
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This work presents a novel technique for embedding color constancy into a saliency-based system for detecting potential landmarks in outdoor environments. Since multiscale color opponencies are among the ingredients determining saliency, the idea is to make such opponencies directly invariant to illumination variations, rather than enforcing the invariance of colors themselves. The new technique is compared against the alternative approach of preprocessing the images with a color constancy procedure before entering the saliency system. The first procedure used in the experimental comparison is the well-known image conversion to chromaticity space, and the second one is based on successive lighting intensity and illuminant color normalizations. The proposed technique offers significant advantages over the preceding two ones since, at a lower computational cost, it exhibits higher stability in front of illumination variations and even of slight viewpoint changes, resulting in a better correspondence of visual saliency to potential landmark elements. (C) 2004 Elsevier B.V. All rights reserved.
引用
收藏
页码:111 / 130
页数:20
相关论文
共 50 条
  • [1] Illumination-invariant color image correction
    Bascle, Benedicte
    Bernier, Olivier
    Lemaire, Vincent
    ADVANCES IN MACHINE VISION, IMAGE PROCESSING, AND PATTERN ANALYSIS, 2006, 4153 : 359 - 368
  • [2] Illumination-invariant color feature representation
    Ko, T
    Bock, P
    8TH WORLD MULTI-CONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL V, PROCEEDINGS: COMPUTER SCIENCE AND ENGINEERING, 2004, : 450 - 455
  • [3] ILLUMINATION-INVARIANT RECOGNITION OF TEXTURE IN COLOR IMAGES
    HEALEY, G
    WANG, LH
    JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1995, 12 (09): : 1877 - 1883
  • [4] Illumination-invariant recognition of texture in color images
    Healey, Glenn
    Wang, Lizhi
    Journal of the Optical Society of America A: Optics and Image Science, and Vision, 1995, 12 (09):
  • [5] An Effective Method for Illumination-Invariant Representation of Color Images
    Horiuchi, Takahiko
    Ibrahim, Abdelhameed
    Kadoi, Hideki
    Tominaga, Shoji
    COMPUTER VISION - ECCV 2012, PT II, 2012, 7584 : 401 - 410
  • [6] Illumination-Invariant Target Color Detection for EMCCD Camera
    Kang, Min-Sung
    Oh, Chang-Beom
    Sohn, Kwang-Hoon
    COLOR SCIENCE AND ENGINEERING SYSTEMS, TECHNOLOGIES, AND APPLICATIONS: TWENTIETH COLOR AND IMAGING CONFERENCE, 2012, : 123 - 127
  • [7] Using eigencolor normalization for illumination-invariant color object recognition
    Lin, ZY
    Wang, JX
    Ma, KK
    PATTERN RECOGNITION, 2002, 35 (11) : 2629 - 2642
  • [8] Block-based illumination-invariant representation for color images
    Ibrahim, Abdelhameed
    Salem, Muhammed
    Ali, Hesham Arafat
    AIN SHAMS ENGINEERING JOURNAL, 2018, 9 (04) : 917 - 926
  • [9] The illumination-invariant matching of deterministic local structure in color images
    Slater, D
    Healey, G
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (10) : 1146 - 1151
  • [10] Illumination-invariant color space and its application to skin-color detection
    Yang, Ukil
    Kim, Bongjoe
    Toh, Kar-Ann
    Sohn, Kwanghoon
    OPTICAL ENGINEERING, 2010, 49 (10)