Integration for 3D structure/motion estimation based on line drawings

被引:0
|
作者
Yang, L [1 ]
Sahli, H [1 ]
机构
[1] Free Univ Brussels, Dept Elect & Informat Proc, IRIS, ETRO, B-1050 Brussels, Belgium
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A general framework for 3D structure/motion analysis is proposed upon integrations of different. visual modules. Line drawings are analyzed from motion point of view, and provide an effective means for 3D reconstruction. 2D motion based and feature correspondences based approaches, are efficiently integrated with the line drawing interpretations under our framework. Normal flow of line segment is employed here to characterize 2D motion and the weighted finite difference method is used for its estimation, in, a simple and practical way. To implement the proposed integration model, an incremental scheme is developed to estimate 3D structure/motion from a sequence of images. Experiments on scenes containing polyhedral objects demonstrate the feasibility of the proposed scheme, and show that the integration of different visual modules gives better 3D structure/motion estimations.
引用
收藏
页码:A413 / A416
页数:4
相关论文
共 50 条
  • [41] Method for 3D motion parameter measurement based on pose estimation
    Wang L.-M.
    Wu X.
    Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition), 2023, 53 (07): : 2099 - 2108
  • [42] Image motion estimation for 3D model based video conferencing
    Cheung, MK
    Tsui, HT
    15TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 3, PROCEEDINGS: IMAGE, SPEECH AND SIGNAL PROCESSING, 2000, : 827 - 830
  • [43] 3D Motion Estimation By Evidence Gathering
    Abuzaina, Anas
    Nixon, Mark S.
    Carter, John N.
    2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2016, : 1756 - 1761
  • [44] Specular motion and 3D shape estimation
    Doevencioglu, Dicle N.
    Ben-Shahar, Ohad
    Barla, Pascal
    Doerschner, Katja
    JOURNAL OF VISION, 2017, 17 (06):
  • [45] Fixation simplifies 3D motion estimation
    Daniilidis, K
    COMPUTER VISION AND IMAGE UNDERSTANDING, 1997, 68 (02) : 158 - 169
  • [46] OpenCL Implementation of Basic Operations for 3D Structure from Motion Estimation
    Mahmoud, Nader
    El-Sisi, Ashraf B.
    2014 9TH INTERNATIONAL CONFERENCE ON INFORMATICS AND SYSTEMS (INFOS), 2014,
  • [47] The 3D line motion matrix and alignment of line reconstructions
    Bartoli, A
    Sturm, P
    2001 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2001, : 287 - 292
  • [48] The 3D Line Motion Matrix and Alignment of Line Reconstructions
    Adrien Bartoli
    Peter Sturm
    International Journal of Computer Vision, 2004, 57 : 159 - 178
  • [49] The 3D line motion matrix and alignment of line reconstructions
    Bartoli, A
    Sturm, P
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 57 (03) : 159 - 178
  • [50] CUDA ACCELERATION OF 3D DYNAMIC SCENE RECONSTRUCTION AND 3D MOTION ESTIMATION FOR MOTION CAPTURE
    Zhang, Zheng
    Seah, Hock Soon
    PROCEEDINGS OF THE 2012 IEEE 18TH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS (ICPADS 2012), 2012, : 284 - 291