Multiview reconstruction of space curves
Författare
Summary, in English
Is the real problem in resolving correspondence using current stereo algorithms the lack of the "right" matching criterion? In studying the related task of reconstructing three-dimensional space curves from their projections in multiple views, we suggest that the problem is more basic: matching and reconstruction are coupled, and so reconstruction algorithms should exploit ths rather than assuming that matching can be successfully performed before reconstruction. To realize this coupling, a generative model of curves is introduced which has two key components: (i) a prior distribution of general space curves and (ii) an image formation model whch discribes how 3D curves are projected onto the image plane. A novel aspect of the image formation model is that it uses an exact description of the gradient field of a piecewise constant image. Based on this forward model, a fully automatic algorithm for solving the inverse problem is developed for an arbitrary number of views. The resulting algorithm is robust to partial occlusion, deficiencies in image curve extraction and it does not rely on photometric information. The relative motion of the cameras is assumed to be given. Several experiments are carried out on various realistic scenarios. In particular, we focus on scenes where traditional correlation-based methods would fail.
Avdelning/ar
Publiceringsår
2003
Språk
Engelska
Sidor
1017-1024
Publikation/Tidskrift/Serie
Proceedings of the IEEE International Conference on Computer Vision
Volym
2
Dokumenttyp
Konferensbidrag
Förlag
IEEE - Institute of Electrical and Electronics Engineers Inc.
Ämne
- Mathematics
Nyckelord
- Stereo algorithms
- Piecewise constant image
- Curve extraction
Conference name
IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, 2003
Conference date
2003-10-13 - 2003-10-16
Conference place
Nice, France
Status
Published
ISBN/ISSN/Övrigt
- CODEN: PICVES