Motion from color

被引：54
作者：
Golland, P
Bruckstein, AM
机构：
[1] Technion Israel Inst Technol, Dept Comp Sci, Ctr Intelligent Syst, IL-32000 Haifa, Israel
[2] MIT, AI Lab, Cambridge, MA 02139 USA
来源：
COMPUTER VISION AND IMAGE UNDERSTANDING | 1997年 / 68卷 / 03期
关键词：
D O I：
10.1006/cviu.1997.0553
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The use of color images for motion estimation is investigated in this work, Beyond the straightforward approach of using the color components as separate images of the same scene, a new method, based on exploiting color invariance under motion, is discussed, Two different sets of color-related, locally computable motion "invariants" are analyzed and tested in this paper, and the results of motion estimation based on them are compared to the direct use of the RGB brightness functions. (C) 1997 Academic Press.
引用
收藏
页码：346 / 362
页数：17
相关论文
共 21 条
  • [1] [Anonymous], P 7 INT C PATT REC M
  • [2] PERFORMANCE OF OPTICAL-FLOW TECHNIQUES
    BARRON, JL
    FLEET, DJ
    BEAUCHEMIN, SS
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 1994, 12 (01) : 43 - 77
  • [3] A SPATIAL PROCESSOR MODEL FOR OBJECT COLOR-PERCEPTION
    BUCHSBAUM, G
    [J]. JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 1980, 310 (01): : 1 - 26
  • [4] Campani M., 1990, Proceedings. Third International Conference on Computer Vision (Cat. No.90CH2934-8), P22, DOI 10.1109/ICCV.1990.139485
  • [5] FINLAYSON GD, 1995, FIFTH INTERNATIONAL CONFERENCE ON COMPUTER VISION, PROCEEDINGS, P720, DOI 10.1109/ICCV.1995.466867
  • [6] HARALICK RM, 1983, P IM UND WORKSH ARL, P84
  • [7] DETERMINING OPTICAL-FLOW
    HORN, BKP
    SCHUNCK, BG
    [J]. ARTIFICIAL INTELLIGENCE, 1981, 17 (1-3) : 185 - 203
  • [8] EXACT REPRODUCTION OF COLORED IMAGES
    HORN, BKP
    [J]. COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1984, 26 (02): : 135 - 167
  • [9] JENNINGS A, 1980, MATRIX COMPUTATION E
  • [10] Lucas B.D., 1981, P IM UND WORKSH, P121
123