A new algorithm for resolving position reversal problems in stereo matching using dynamic programming

Minoru Fujii, Yasuo Matsuyama

    Research output: Contribution to journalArticle

    Abstract

    In binocular stereo vision, since color and distance information can be obtained simultaneously by a passive method which will not affect the environment, it is expected to be commonly used in the vision of future mobile robots. However, it is necessary to solve difficult problems such as finding corresponding points in the right and left images. Many stereo algorithms dealing with this problem have been proposed so far, all with their own weaknesses. This paper considers the position reversal problem, in which the positions of the corresponding points change places on the right and left scan lines. This is a subject in which there has been little progress despite its importance in obstacle detection by mobile robots. It has been considered that the position reversal problem cannot be processed correctly in plain dynamic programming for global matching unless the assumption that the positions of the corresponding points do not change places is forced. In the method proposed in this paper, four states are set in the search for the corresponding points. The search using dynamic programming is performed in two stages so that the position reversal problem can be solved while the above assumption is maintained. Then, matching also becomes possible in the case of objects for which the positions of the corresponding points change places. The proposed method is experimentally applied to the search problem in which the positions of the corresponding points change places inside scan lines, and its effectiveness is verified.

    Original languageEnglish
    Pages (from-to)25-35
    Number of pages11
    JournalSystems and Computers in Japan
    Volume28
    Issue number4
    Publication statusPublished - 1997 Apr

    Fingerprint

    Stereo Matching
    Reversal
    Dynamic programming
    Mobile robots
    Dynamic Programming
    Binoculars
    Stereo vision
    Change Point
    Color
    Mobile Robot
    Obstacle Detection
    Stereo Vision
    Line
    Search Problems
    Necessary

    Keywords

    • Binocular stereo vision
    • Dynamic programming
    • Mobile robot
    • Robot vision
    • Stereo matching

    ASJC Scopus subject areas

    • Hardware and Architecture
    • Information Systems
    • Theoretical Computer Science
    • Computational Theory and Mathematics

    Cite this

    A new algorithm for resolving position reversal problems in stereo matching using dynamic programming. / Fujii, Minoru; Matsuyama, Yasuo.

    In: Systems and Computers in Japan, Vol. 28, No. 4, 04.1997, p. 25-35.

    Research output: Contribution to journalArticle

    @article{10abdc9fc92e470f894050c1ee84ba17,
    title = "A new algorithm for resolving position reversal problems in stereo matching using dynamic programming",
    abstract = "In binocular stereo vision, since color and distance information can be obtained simultaneously by a passive method which will not affect the environment, it is expected to be commonly used in the vision of future mobile robots. However, it is necessary to solve difficult problems such as finding corresponding points in the right and left images. Many stereo algorithms dealing with this problem have been proposed so far, all with their own weaknesses. This paper considers the position reversal problem, in which the positions of the corresponding points change places on the right and left scan lines. This is a subject in which there has been little progress despite its importance in obstacle detection by mobile robots. It has been considered that the position reversal problem cannot be processed correctly in plain dynamic programming for global matching unless the assumption that the positions of the corresponding points do not change places is forced. In the method proposed in this paper, four states are set in the search for the corresponding points. The search using dynamic programming is performed in two stages so that the position reversal problem can be solved while the above assumption is maintained. Then, matching also becomes possible in the case of objects for which the positions of the corresponding points change places. The proposed method is experimentally applied to the search problem in which the positions of the corresponding points change places inside scan lines, and its effectiveness is verified.",
    keywords = "Binocular stereo vision, Dynamic programming, Mobile robot, Robot vision, Stereo matching",
    author = "Minoru Fujii and Yasuo Matsuyama",
    year = "1997",
    month = "4",
    language = "English",
    volume = "28",
    pages = "25--35",
    journal = "Systems and Computers in Japan",
    issn = "0882-1666",
    publisher = "John Wiley and Sons Inc.",
    number = "4",

    }

    TY - JOUR

    T1 - A new algorithm for resolving position reversal problems in stereo matching using dynamic programming

    AU - Fujii, Minoru

    AU - Matsuyama, Yasuo

    PY - 1997/4

    Y1 - 1997/4

    N2 - In binocular stereo vision, since color and distance information can be obtained simultaneously by a passive method which will not affect the environment, it is expected to be commonly used in the vision of future mobile robots. However, it is necessary to solve difficult problems such as finding corresponding points in the right and left images. Many stereo algorithms dealing with this problem have been proposed so far, all with their own weaknesses. This paper considers the position reversal problem, in which the positions of the corresponding points change places on the right and left scan lines. This is a subject in which there has been little progress despite its importance in obstacle detection by mobile robots. It has been considered that the position reversal problem cannot be processed correctly in plain dynamic programming for global matching unless the assumption that the positions of the corresponding points do not change places is forced. In the method proposed in this paper, four states are set in the search for the corresponding points. The search using dynamic programming is performed in two stages so that the position reversal problem can be solved while the above assumption is maintained. Then, matching also becomes possible in the case of objects for which the positions of the corresponding points change places. The proposed method is experimentally applied to the search problem in which the positions of the corresponding points change places inside scan lines, and its effectiveness is verified.

    AB - In binocular stereo vision, since color and distance information can be obtained simultaneously by a passive method which will not affect the environment, it is expected to be commonly used in the vision of future mobile robots. However, it is necessary to solve difficult problems such as finding corresponding points in the right and left images. Many stereo algorithms dealing with this problem have been proposed so far, all with their own weaknesses. This paper considers the position reversal problem, in which the positions of the corresponding points change places on the right and left scan lines. This is a subject in which there has been little progress despite its importance in obstacle detection by mobile robots. It has been considered that the position reversal problem cannot be processed correctly in plain dynamic programming for global matching unless the assumption that the positions of the corresponding points do not change places is forced. In the method proposed in this paper, four states are set in the search for the corresponding points. The search using dynamic programming is performed in two stages so that the position reversal problem can be solved while the above assumption is maintained. Then, matching also becomes possible in the case of objects for which the positions of the corresponding points change places. The proposed method is experimentally applied to the search problem in which the positions of the corresponding points change places inside scan lines, and its effectiveness is verified.

    KW - Binocular stereo vision

    KW - Dynamic programming

    KW - Mobile robot

    KW - Robot vision

    KW - Stereo matching

    UR - http://www.scopus.com/inward/record.url?scp=0031119863&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0031119863&partnerID=8YFLogxK

    M3 - Article

    AN - SCOPUS:0031119863

    VL - 28

    SP - 25

    EP - 35

    JO - Systems and Computers in Japan

    JF - Systems and Computers in Japan

    SN - 0882-1666

    IS - 4

    ER -