Pose determination of human faces by using vanishing points

被引:21
|
作者
Wang, JG [1 ]
Sung, E [1 ]
机构
[1] Nanyang Technol Univ, Sch Elect & Elect Engn, Div Control & Instrumentat, Singapore 639798, Singapore
关键词
real-time face tracking; pose estimation; vanishing point; projective geometry; ratio; human-machine interaction;
D O I
10.1016/S0031-3203(00)00154-0
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A new method for estimating 3D-head pose from a monocular image is proposed in this paper. The approach employs general prior knowledge of face structure and the corresponding geometrical constraints provided by the location of vanishing point to determine pose of human faces. The connection of the two far-eye corners and the two neighboring-eye corners, respectively, form the eye-lines. Connecting the two far-mouth corners forms the mouth-line. The eye-lines and the mouth-line are assumed parallel in 3D space, and their vanishing point on the image plane can be used to infer 3D pose of the human face. Perspective projection imaging model is used and an accurate analytic solution of pose (position and orientation) of human face is deduced. The orientation of the facial plane can be obtained when the ratio of the lengths of the eye-line segment (far-eye corners) and the mouth-line segment (far-mouth corners) is known. Furthermore, if one of the two lengths is known, then the absolute positions of the feature corners can be located. The robustness analysis of the algorithm with synthetic data and the experimental results of real face images are enclosed. (C) 2001 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.
引用
收藏
页码:2427 / 2445
页数:19
相关论文
共 50 条
  • [1] CONTRIBUTION TO THE DETERMINATION OF VANISHING POINTS USING HOUGH TRANSFORM
    LUTTON, E
    MAITRE, H
    LOPEZKRAHE, J
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1994, 16 (04) : 430 - 438
  • [2] Monocular-based Pose Estimation Using Vanishing Points for Indoor Image Correction
    Gakne, Paul Verlaine
    O'Keefe, Kyle
    [J]. 2017 INTERNATIONAL CONFERENCE ON INDOOR POSITIONING AND INDOOR NAVIGATION (IPIN), 2017,
  • [3] Pose and Focal Length Estimation Using Two Vanishing Points with Known Camera Position
    Guo, Kai
    Cao, Rui
    Tian, Ye
    Ji, Binyuan
    Dong, Xuefeng
    Li, Xuyang
    [J]. SENSORS, 2023, 23 (07)
  • [4] An analytic solution for the pose determination of human faces from a monocular image
    Ho, SY
    Huang, HL
    [J]. PATTERN RECOGNITION LETTERS, 1998, 19 (11) : 1045 - 1054
  • [5] Camera pose determination based on 4 coplanar points using tori parameters
    Caramelo, FJ
    Ferreira, NC
    Lima, JJP
    [J]. Proceedings of the Fifth IASTED International Conference on Visualization, Imaging, and Image Processing, 2005, : 640 - 644
  • [6] ROAD FOLLOWING USING VANISHING POINTS
    LIOU, SP
    JAIN, RC
    [J]. COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1987, 39 (01): : 116 - 130
  • [7] USING VANISHING POINTS FOR CAMERA CALIBRATION
    CAPRILE, B
    TORRE, V
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 1990, 4 (02) : 127 - 139
  • [8] Active intrinsic calibration using vanishing points
    Daniilidis, K
    Ernst, J
    [J]. 1996 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1996, : 708 - 713
  • [9] 'VANISHING POINTS'
    PAGANO, E
    [J]. POET LORE, 1987, 82 (03): : 157 - 157
  • [10] VANISHING POINTS
    QUARZOCERINA, MP
    [J]. DU-DIE ZEITSCHRIFT DER KULTUR, 1984, (10): : 96 - 97