Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition最新文献

Urban intersections are the most dangerous parts of a blind or visually impaired person's travel. To address this problem, this paper describes the novel "Crosswatch" system, which uses computer vision to provide information about the location and orientation of crosswalks to a blind or visually impaired pedestrian holding a camera cell phone. A prototype of the system runs on an off-the-shelf Nokia N95 camera phone in real time, which automatically takes a few images per second, analyzes each image in a fraction of a second and sounds an audio tone when it detects a crosswalk. Real-time performance on the cell phone, whose computational resources are limited compared to the type of desktop platform usually used in computer vision, is made possible by coding in Symbian C++. Tests with blind subjects demonstrate the feasibility of the system.

We describe a method for segmenting neural fiber bundles in diffusion-weighted magnetic resonance images (DWMRI). As these bundles traverse the brain to connect regions, their local orientation of diffusion changes drastically, hence a constant global model is inaccurate. We propose a method to compute localized statistics on orientation information and use it to drive a variational active contour segmentation that accurately models the non-homogeneous orientation information present along the bundle. Initialized from a single fiber path, the proposed method proceeds to capture the entire bundle. We demonstrate results using the technique to segment the cingulum bundle and describe several extensions making the technique applicable to a wide range of tissues.

In this paper, we describe a nonlinear image representation based on divisive normalization that is designed to match the statistical properties of photographic images, as well as the perceptual sensitivity of biological visual systems. We decompose an image using a multi-scale oriented representation, and use Student's t as a model of the dependencies within local clusters of coefficients. We then show that normalization of each coefficient by the square root of a linear combination of the amplitudes of the coefficients in the cluster reduces statistical dependencies. We further show that the resulting divisive normalization transform is invertible and provide an efficient iterative inversion algorithm. Finally, we probe the statistical and perceptual advantages of this image representation by examining its robustness to added noise, and using it to enhance image contrast.

We propose a novel representation of continuous, closed curves in ℝ(n) that is quite efficient for analyzing their shapes. We combine the strengths of two important ideas - elastic shape metric and path-straightening methods -in shape analysis and present a fast algorithm for finding geodesics in shape spaces. The elastic metric allows for optimal matching of features while path-straightening provides geodesics between curves. Efficiency results from the fact that the elastic metric becomes the simple (2) metric in the proposed representation. We present step-by-step algorithms for computing geodesics in this framework, and demonstrate them with 2-D as well as 3-D examples.

Object-based segmentation is a challenging topic. Most of the previous algorithms focused on segmenting a single or a small set of objects. In this paper, the multiple class object-based segmentation is achieved using the appearance and bag of keypoints models integrated over mean-shift patches. We also propose a novel affine invariant descriptor to model the spatial relationship of keypoints and apply the Elliptical Fourier Descriptor to describe the global shapes. The algorithm is computationally efficient and has been tested for three real datasets using less training samples. Our algorithm provides better results than other studies reported in the literature.

This paper illustrates and extends an efficient framework, called the square-root-elastic (SRE) framework, for studying shapes of closed curves, that was first introduced in [2]. This framework combines the strengths of two important ideas - elastic shape metric and path-straightening methods - for finding geodesics in shape spaces of curves. The elastic metric allows for optimal matching of features between curves while path-straightening ensures that the algorithm results in geodesic paths. This paper extends this framework by removing two important shape preserving transformations: rotations and re-parameterizations, by forming quotient spaces and constructing geodesics on these quotient spaces. These ideas are demonstrated using experiments involving 2D and 3D curves.

This paper proposes a method to match diffusion tensor magnetic resonance images (DT-MRI) through the large deformation diffeomorphic metric mapping of tensor fields on the image volume, resulting in optimizing for geodesics on the space of diffeomorphisms connecting two diffusion tensor images. A coarse to fine multi-resolution and multi-kernel-width scheme is detailed, to reduce both ambiguities and computation load. This is illustrated by numerical experiments on DT-MRI brain and images.

In this paper, we propose a novel and robust algorithm for the groupwise non-rigid registration of multiple unlabeled point-sets with no bias toward any of the given point-sets. To quantify the divergence between multiple probability distributions each estimated from the given point sets, we develop a novel measure based on their cumulative distribution functions that we dub the CDF-JS divergence. The measure parallels the well known Jensen-Shannon divergence (defined for probability density functions) but is more regular than the JS divergence since its definition is based on CDFs as opposed to density functions. As a consequence, CDF-JS is more immune to noise and statistically more robust than the JS.We derive the analytic gradient of the CDF-JS divergence with respect to the non-rigid registration parameters for use in the numerical optimization of the groupwise registration leading a computationally efficient and accurate algorithm. The CDF-JS is symmetric and has no bias toward any of the given point-sets, since there is NO fixed reference data set. Instead, the groupwise registration takes place between the input data sets and an evolving target dubbed the pooled model. This target evolves to a fully registered pooled data set when the CDF-JS defined over this pooled data is minimized. Our algorithm is especially useful for creating atlases of various shapes (represented as point distribution models) as well as for simultaneously registering 3D range data sets without establishing any correspondence. We present experimental results on non-rigid registration of 2D/3D real point set data.

In this paper, we present a novel and robust spline approximation algorithm given a noisy symmetric positive definite (SPD) tensor field. Such tensor fields commonly arise in the field of Medical Imaging in the form of Diffusion Tensor (DT) MRI data sets. We develop a statistically robust algorithm for constructing a tensor product of B-splines - for approximating and interpolating these data - using the Riemannian metric of the manifold of SPD tensors. Our method involves a two step procedure wherein the first step uses Riemannian distances in order to evaluate a tensor spline by computing a weighted intrinsic average of diffusion tensors and the second step involves minimization of the Riemannian distance between the evaluated spline curve and the given data. These two steps are alternated to achieve the desired tensor spline approximation to the given tensor field. We present comparisons of our algorithm with four existing methods of tensor interpolation applied to DT-MRI data from fixed heart slices of a rabbit, and show significantly improved results in the presence of noise and outliers. We also present validation results for our algorithm using synthetically generated noisy tensor field data with outliers. This interpolation work has many applications e.g., in DT-MRI registration, in DT-MRI Atlas construction etc. This research was in part funded by the NIH ROI NS42075 and the Department of Radiology, University of Florida.

Segmentation involves separating an object from the background. In this work, we propose a novel segmentation method combining image information with prior shape knowledge, within the level-set framework. Following the work of Leventon et al., we revisit the use of principal component analysis (PCA) to introduce prior knowledge about shapes in a more robust manner. To this end, we utilize Kernel PCA and show that this method of learning shapes outperforms linear PCA, by allowing only shapes that are close enough to the training data. In the proposed segmentation algorithm, shape knowledge and image information are encoded into two energy functionals entirely described in terms of shapes. This consistent description allows to fully take advantage of the Kernel PCA methodology and leads to promising segmentation results. In particular, our shape-driven segmentation technique allows for the simultaneous encoding of multiple types of shapes, and offers a convincing level of robustness with respect to noise, clutter, partial occlusions, or smearing.