Quantitative analysis of the viewpoint consistency constraint in model-based vision
- 30 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 632-639
- https://doi.org/10.1109/iccv.1993.378152
Abstract
The authors present a quantitative analysis of the viewpoint consistency constraint (VCC), which is the fundamental principle behind model-based methods for recognizing 3-D objects from 2-D data. It defines a measure of viewpoint consistency error (VCE), based on a formal model of image feature errors. Existing methods for establishing feature correspondences using the VCC are discussed. The poor performance of incremental methods is demonstrated and attributed to the failure to ensure that global consistency improves during search. A more reliable method, viewpoint consistency ascent, which uses the VCE explicitly as a heuristic for a state-space search, is presented. The two algorithms are compared in an experimental study. The approach to quantitative analysis of alternative algorithms is illustrated, which may be applied to model based object recognition more generally.<>Keywords
This publication has 10 references indexed in Scilit:
- Three-dimensional object recognition from single two-dimensional imagesPublished by Elsevier ,2003
- 3D grouping by viewpoint consistency ascentImage and Vision Computing, 1992
- Modelling Data Complexity for Model-based VisionPublished by Springer Nature ,1992
- Model-based TrackingPublished by Springer Nature ,1991
- Relational Model Construction and 3D Object Recognition from Single 2D Monochromatic ImagePublished by British Machine Vision Association and Society for Pattern Recognition ,1991
- Experiments on the use of the ATMS to label features for object recognitionPublished by Springer Nature ,1990
- Model based perspective inversionImage and Vision Computing, 1989
- Model Based Vision using a Planar Representation of the ViewspherePublished by British Machine Vision Association and Society for Pattern Recognition ,1988
- Alvey MMI-007 Vehicle Exemplar: Performance and LimitationsPublished by British Machine Vision Association and Society for Pattern Recognition ,1987
- Model-Based Recognition and Localization from Sparse Range or Tactile DataThe International Journal of Robotics Research, 1984