The solutions to many vision problems involve integrating measurements from multiple sources. Most existing methods rely on a hidden assumption, i.e., these measurements are consistent. In reality, unfortunately, this...
详细信息
In this paper, we present a novel stereo algorithm that combines the strengths of region-based stereo and dynamic programming on a tree approaches. Instead of formulating an image as individual scan-lines or as a pixe...
详细信息
Markov random field models provide a robust and unified framework for early vision problems such as stereo and image restoration. Inference algorithms based on graph cuts and belief propagation have been found to yiel...
详细信息
Markov random field models provide a robust and unified framework for early vision problems such as stereo and image restoration. Inference algorithms based on graph cuts and belief propagation have been found to yield accurate results, but despite recent advances are often too slow for practical use. In this paper we present some algorithmic techniques that substantially improve the running time of the loopy belief propagation approach. One of the techniques reduces the complexity of the inference algorithm to be linear rather than quadratic in the number of possible labels for each pixel, which is important for problems such as image restoration that have a large label set. Another technique speeds up and reduces the memory requirements of belief propagation on grid graphs. A third technique is a multi-grid method that makes it possible to obtain good results with a small fixed number of message passing iterations, independent of the size of the input images. Taken together these techniques speed up the standard algorithm by several orders of magnitude. In practice we obtain results that are as accurate as those of other global methods (e.g., using the Middlebury stereo benchmark) while being nearly as fast as purely local methods.
The Fisher Linear Discriminant (FLD) is commonly used in patternrecognition. It finds a linear subspace that maximally separates class patterns according to Fisher's Criterion. Several methods of computing the FL...
详细信息
This paper presents a novel interactive Projector Calibration for arbitrary Multi-Projector-Camera environments. The method does not require any calibration rig and is not restricted to any special arrangement of the ...
详细信息
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a low-dimensional embedding of human motion data, with a density funct...
详细信息
This paper presents an extension to category classification with bag-of-features, which represents an image as an orderless distribution of features. We propose a method to exploit spatial relations between features b...
详细信息
This paper presents a shape representation and a variational framework for the construction of diffeomorphisms that establish "meaningful" correspondences between images, in that they preserve the local geom...
详细信息
In this paper, we study disjoint information as a metric for image comparison and its applications in image matching, alignment, and video tracking. Disjoint information is the joint entropy of random variables exclud...
详细信息
In its full generality, motion analysis of crowded objects necessitates recognition and segmentation of each moving entity. The difficulty of these tasks increases considerably with occlusions and therefore with crowd...
详细信息
暂无评论