A silhouette-based algorithm for texture registration and stitching

被引:78
|
作者
Lensch, HPA [1 ]
Heidrich, W
Seidel, HP
机构
[1] Max Planck Inst Informat, Saarbrucken, Germany
[2] Univ British Columbia, Vancouver, BC V5Z 1M9, Canada
关键词
texture stitching; 3D-2D registration; object representation;
D O I
10.1006/gmod.2001.0554
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
In this paper a system is presented that automatically registers and stitches textures acquired from multiple photographic images onto the surface of a given corresponding 3D model. Within this process the camera position, direction, and field of view must be determined for each of the images. For this registration, which aligns a 2D image to a 3D model, we present an efficient hardware-accelerated silhouette-based algorithm working on different image resolutions that accurately registers each image without any user interaction. Besides the silhouettes, the given texture information also can be used to improve accuracy by comparing one stitched texture to already registered images resulting in a global multiview optimization. After the 3D-2D registration for each part of the 3D model's surface the view is determined which provides the best available texture. Textures are blended at the borders of regions assigned to different Views. (C) 2001 Elsevier Science (USA).
引用
收藏
页码:245 / 262
页数:18
相关论文
共 50 条
  • [31] Gait flow image: A silhouette-based gait representation for human identification
    Lam, Toby H. W.
    Cheung, K. H.
    Liu, James N. K.
    PATTERN RECOGNITION, 2011, 44 (04) : 973 - 987
  • [32] Boosting Robustness of Silhouette-Based Gait Recognition Against Adversarial Attacks
    Ji, Bingbing
    Chen, Xin
    Yang, Wenhao
    Zhu, Futian
    ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT V, ICIC 2024, 2024, 14866 : 72 - 84
  • [33] VIHASI: VIRTUAL HUMAN ACTION SILHOUETTE DATA FOR THE PERFORMANCE EVALUATION OF SILHOUETTE-BASED ACTION RECOGNITION METHODS
    Ragheb, Hossein
    Velastin, Sergio
    Remagnino, Paolo
    Ellis, Tim
    2008 SECOND ACM/IEEE INTERNATIONAL CONFERENCE ON DISTRIBUTED SMART CAMERAS, 2008, : 505 - 514
  • [34] Silhouette-based occluded object recognition through curvature scale space
    Mokhtarian, F
    MACHINE VISION AND APPLICATIONS, 1997, 10 (03) : 87 - 97
  • [35] Silhouette-based human action recognition using SAX-Shapes
    Junejo, Imran N.
    Junejo, Khurrum Nazir
    Al Aghbari, Zaher
    VISUAL COMPUTER, 2014, 30 (03): : 259 - 269
  • [36] Silhouette-based human action recognition using SAX-Shapes
    Imran N. Junejo
    Khurrum Nazir Junejo
    Zaher Al Aghbari
    The Visual Computer, 2014, 30 : 259 - 269
  • [37] Silhouette-based method for object classification and human action recognition in video
    Dedeoglu, Yigithan
    Toreyin, B. Ugur
    Gudukbay, Ugur
    Cetin, A. Enis
    COMPUTER VISION IN HUMAN-COMPUTER INTERACTION, 2006, 3979 : 64 - 77
  • [38] Gait Recognition using Spatio-temporal Silhouette-based Features
    Sabir, Azhin
    Al-jawad, Naseer
    Jassim, Sabah
    MOBILE MULTIMEDIA/IMAGE PROCESSING, SECURITY, AND APPLICATIONS 2013, 2013, 8755
  • [39] Silhouette-based occluded object recognition through curvature scale space
    Univ of Surrey, Guildford, United Kingdom
    Mach Vision Appl, 3 (87-97):
  • [40] Silhouette-Based Multi-View Human Action Recognition in Video
    Aryanfar, Alihossein
    Yaakob, Razali
    Halin, Alfian Abdul
    Sulaiman, Md Nasir
    Kasmiran, Khairul Azhar
    2014 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND TECHNOLOGY (ICCST), 2014,