We introduce 'Joint Feature Distributions', a general statistical framework for feature based multi-image matching that explicitly models the joint probability distributions of corresponding features across several images. Conditioning on feature positions in some of the images gives well-localized distributions for their correspondents in the others, and hence tight likelihood regions for correspondence search. We apply the framework in the simplest case of Gaussian-like distributions over the direct sum (affine images) and tensor product (projective images) of the image coordinates. This produces probabilistic correspondence models that generalize the geometric multi-image matching constraints, roughly speaking by a form of model-averaging over them. These very simple methods predict accurate correspondence likelihood regions for any scene geometry including planar and near-planar scenes, without ill-conditioning or explicit model selection. Small amounts of distortion and non-rigidity are also tolerated. We develop the theory for any number of affine or projective images, explain its relationship to matching tensors, and give results for an initial implementation.
Joint feature distributions for image correspondence
Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 ; 2 ; 201-208 vol.2
2001-01-01
954420 byte
Conference paper
Electronic Resource
English
Joint Feature Distributions for Image Correspondence
British Library Conference Proceedings | 2001
|Global image feature correspondence under a multi-image network
British Library Online Contents | 1999
|Entropy-of-likelihood Feature Selection for Image Correspondence
British Library Conference Proceedings | 2003
|Joint Inference in Weakly-Annotated Image Datasets via Dense Correspondence
British Library Online Contents | 2016
|