Object reconstruction and pose indexing by volume feedback

TitleObject reconstruction and pose indexing by volume feedback
Publication TypeConference Paper
Year of Publication2003
AuthorsAvanaki, A. N., B. Hamidzadeh, and F. Kossentini
Conference NameImage Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on
PaginationII - 13-16 vol.3
Date Publishedsep.
Keywords3D object tracking, content-based retrieval, image reconstruction, image retrieval, image sequences, image texture, monocular video sequences, object reconstruction, pose indexing, shape-from-silhouette volume reconstruction, video signal processing, volume feedback

Three dimensional reconstruction of a rigid object from monocular video sequences is addressed. Initially object pose is estimated in each image by locating similar (unknown) textures assuming flat depth maps for all input images. Shape-from-silhouette Szeliski (1993) is then applied to make a 3-D model (volume), which is used for a new round of pose estimation, this time by a model-based method giving better estimates. Before repeating this process by building a new volume, pose estimates are adjusted to reduce error by maximizing a quality measure for shape-from-silhouette volume reconstruction. The volume feedback is terminated when pose estimates do not change much as compared to those produced by previous iteration. The final output is a pose index (the last set of pose estimates) and a volume. Good performance of the system is shown by several experiments. No model is assumed for the object. Feature points are neither detected nor tracked: no problematic feature matching or correspondence. The high-level pose index generated for input images can be used for content-based retrieval. Our method can be also applied to 3-D object tracking in video.


a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2021 The University of British Columbia