Three-dimensional object recognition using two-dimensional complex amplitude including three-dimensional shape information

被引:0
|
作者
Yoshikawa, N [1 ]
Suzuki, Y [1 ]
机构
[1] Musashi Inst Technol, Fac Engn, Dept Elect & Commun Engn, Setagaya Ku, Tokyo 1588557, Japan
来源
OPTOMECHATRONIC SYSTEMS IV | 2003年 / 5264卷
关键词
fringe pattern correlator; Fourier transform profilometry; three-dimensional object recognition;
D O I
10.1117/12.515008
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The fringe pattern correlator (FPC) can recognize 3D objects using a height transformed complex amplitude as 3D information. The height transformed complex amplitude is a two-dimensional (2D) complex amplitude whose phase factor includes actual height information of 3D objects. The FPC can perform effective 3D correlation using 2D correlation with the height transformed complex amplitude. In this study, we describe the effect of the amplitude factor of the height transformed complex amplitude in the FPC. The amplitude factor represents contrast information of the projected grating on the object, which corresponds to the reflectance property depending on 3D shape. We classify the amplitude factor by the 3D shape (flat surface, slope, edge, large step) and other factor (illumination condition, shadow, random pattern). We present the recognition characteristics with respect to the amplitude factor.
引用
收藏
页码:66 / 73
页数:8
相关论文
共 50 条
  • [31] A three-dimensional topographic survey based on two-dimensional image information
    Song, Xiao-long
    Bai, Yu-chuan
    Ying, Chao
    JOURNAL OF ZHEJIANG UNIVERSITY-SCIENCE A, 2014, 15 (01): : 68 - 82
  • [32] Three-dimensional volume containing multiple two-dimensional information patterns
    Hirotaka Nakayama
    Atsushi Shiraki
    Ryuji Hirayama
    Nobuyuki Masuda
    Tomoyoshi Shimobaba
    Tomoyoshi Ito
    Scientific Reports, 3
  • [33] A three-dimensional topographic survey based on two-dimensional image information
    Xiao-long Song
    Yu-chuan Bai
    Chao Ying
    Journal of Zhejiang University SCIENCE A, 2014, 15 : 68 - 82
  • [34] Three-dimensional volume containing multiple two-dimensional information patterns
    Nakayama, Hirotaka
    Shiraki, Atsushi
    Hirayama, Ryuji
    Masuda, Nobuyuki
    Shimobaba, Tomoyoshi
    Ito, Tomoyoshi
    SCIENTIFIC REPORTS, 2013, 3
  • [35] Obtaining a nonsingular two-dimensional cloak of complex shape from a perfect three-dimensional cloak
    Zhang, Pu
    Jin, Yi
    He, Sailing
    APPLIED PHYSICS LETTERS, 2008, 93 (24)
  • [36] Two-Dimensional Simplification of Complex Three-Dimensional Wire Mesh Screens
    Okolo, Patrick N.
    Zhao, Kun
    Kennedy, John
    Mgbemena, Chigbo
    Eke, Mkpamdi
    Bennett, Gareth J.
    JOURNAL OF AEROSPACE ENGINEERING, 2021, 34 (06)
  • [37] Surface matching for object recognition in complex three-dimensional scenes
    Johnson, AE
    Hebert, M
    IMAGE AND VISION COMPUTING, 1998, 16 (9-10) : 635 - 651
  • [38] Three-dimensional shape visualization of object in impact
    Zhang, QC
    Su, XY
    ICO20: OPTICAL INFORMATION PROCESSING, PTS 1 AND 2, 2006, 6027
  • [39] Three-dimensional object recovery from two-dimensional images: A new approach
    Brown, EW
    Wang, P
    INTELLIGENT ROBOTS AND COMPUTER VISION XV: ALGORITHMS, TECHNIQUES, ACTIVE VISION, AND MATERIALS HANDLING, 1996, 2904 : 138 - 147
  • [40] Three-dimensional object recognition is viewpoint dependent
    Michael J. Tarr
    Pepper Williams
    William G. Hayward
    Isabel Gauthier
    Nature Neuroscience, 1998, 1 : 275 - 277