Three-dimensional object recognition from single two-dimensional images

DMCA

Three-dimensional object recognition from single two-dimensional images (1987)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by David G. Lowe

Venue:	Artificial Intelligence
Citations:	484 - 7 self

BibTeX

@ARTICLE{Lowe87three-dimensionalobject,
    author = {David G. Lowe},
    title = {Three-dimensional object recognition from single two-dimensional images},
    journal = {Artificial Intelligence},
    year = {1987},
    pages = {355--395}
}

OpenURL

Abstract

A computer vision system has been implemented that can recognize threedimensional objects from unknown viewpoints in single gray-scale images. Unlike most other approaches, the recognition is accomplished without any attempt to reconstruct depth information bottom-up from the visual input. Instead, three other mechanisms are used that can bridge the gap between the two-dimensional image and knowledge of three-dimensional objects. First, a process of perceptual organization is used to form groupings and structures in the image that are likely to be invariant over a wide range of viewpoints. Second, a probabilistic ranking method is used to reduce the size of the search space during model based matching. Finally, a process of spatial correspondence brings the projections of three-dimensional models into direct correspondence with the image by solving for unknown viewpoint and model parameters. A high level of robustness in the presence of occlusion and missing data can be achieved through full application of a viewpoint consistency constraint. It is argued that similar mechanisms and constraints form the basis for recognition in human vision. This paper has been published in Artificial Intelligence, 31, 3 (March 1987), pp. 355–395. 1 1

Keyphrases

three-dimensional object recognition single two-dimensional image unknown viewpoint three-dimensional object direct correspondence depth information bottom-up wide range threedimensional object full application two-dimensional image search space spatial correspondence three-dimensional model probabilistic ranking method model parameter artificial intelligence single gray-scale image computer vision system viewpoint consistency constraint high level human vision similar mechanism visual input perceptual organization

DMCA