In this paper we discuss a hybrid technique for piecewise-smooth optical flow estimation. We first pose optical flow estimation as a gradient-based local regression problem and solve it under a high-breakdown robust c...
详细信息
ISBN:
(纸本)0769512720
In this paper we discuss a hybrid technique for piecewise-smooth optical flow estimation. We first pose optical flow estimation as a gradient-based local regression problem and solve it under a high-breakdown robust criterion. Then taking the output from the first step as the initial guess, we recast the problem in a robust matching-based global optimization framework. We have developed novel fast-converging deterministic algorithms for both optimization problems and incorporated a hierarchical scheme to handle large motions. This technique inherits the good subpixel accuracy from the local gradient approach and the insensitivity to local perturbation and derivative quality from the global matching approach, and it overcomes the limitations of both. Significant advantages over competing techniques are demonstrated on various standard synthetic and real image sequences.
A robust, multi-frame, progressive refinement framework for registering narrow field of view video to reference imagery is presented. A major strength of the approach is its effectiveness in the presence of dissimilar...
详细信息
ISBN:
(纸本)0769512720
A robust, multi-frame, progressive refinement framework for registering narrow field of view video to reference imagery is presented. A major strength of the approach is its effectiveness in the presence of dissimilar video and reference image appearance. Normalized oriented energy image pyramids are employed to enable alignment of images with global visual dissimilarities, yet local feature commonality. Local matching is then applied coarse-to-fine, along four dimensions: spatial frequency, local support, search range, and model order (a robust parametric model fit is used to reject outliers at each iteration). Globally optimal multi-frame alignment is obtained with respect to several constraints: frame-to-reference local matches, recovered frame-to-frame motion, and optional a priori estimates of sensor pose. The framework is described in detail and applied to two examples: aerial video to geographic reference image alignment (georegistration) and retinal slit lamp video to fundus image alignment.
We present a new feature based algorithm for stereo correspondence. Most of the previous feature based methods match sparse features like edge pixels, producing only sparse disparity maps. Our algorithm detects and ma...
详细信息
ISBN:
(纸本)0769512720
We present a new feature based algorithm for stereo correspondence. Most of the previous feature based methods match sparse features like edge pixels, producing only sparse disparity maps. Our algorithm detects and matches dense features between the left and right images of a stereo pair, producing a semi-dense disparity map. Our dense feature is defined with respect to both images of a stereo pair, and it is computed during the stereo matching process, not a preprocessing.step. In essence, a dense feature is a connected set of pixels in the left image and a corresponding set of pixels in the right image such that the intensity edges on the boundary of these sets are stronger than their matching error (which is basically the difference in intensities between corresponding boundary pixels). Our algorithm produces accurate semi-dense disparity maps, leaving featureless regions in the scene unmatched It is robust, requires little parameter tuning, can handle brightness differences between images, and is fast (linear complexity).
Representing images with layers has many important applications, such as video compression, motion analysis, and 3D scene analysis. This paper presents an approach to reliably extracting layers from images by taking a...
详细信息
ISBN:
(纸本)0769512720
Representing images with layers has many important applications, such as video compression, motion analysis, and 3D scene analysis. This paper presents an approach to reliably extracting layers from images by taking advantages of the fact that homographies induced by planar patches in the scene form a low dimensional linear subspace. Layers in the input images will be mapped in the subspace, where it is proven that they form well-defined clusters and can be reliably identified by a simple mean-shift based clustering algorithm. Global optimality is achieved since all valid regions are simultaneously taken into account, and noise can be effectively reduced by enforcing the subspace constraint. Good layer descriptions are shown to be extracted in the experimental results.
The paper presents a novel processing.scheme for the automatic computation of a medial shape model which is representative for an object population with shape variability. The sensitivity of medial descriptions to obj...
详细信息
ISBN:
(纸本)0769512720
The paper presents a novel processing.scheme for the automatic computation of a medial shape model which is representative for an object population with shape variability. The sensitivity of medial descriptions to object variations and small boundary perturbations are fundamental problems of any skeletonization technique. These problems are approached with the computation of a model with common medial branching topology and grid sampling. This model is then used for a medial shape description of individual objects via a constrained model fit. The process starts from parametric 3D boundary representations with existing point-to-point homology between objects. The Voronoi diagram of each sampled object boundary is grouped into medial sheets and simplified by a pruning algorithm using a volumetric contribution criterion. Medial sheets are combined to form a common medial branching topology. Finally, the medial sheets are sampled and represented as meshes of medial primitives. We present new results on populations of up to 184 biological objects. For these objects, the common medial branching topology is described by a small number of sheets. Despite the coarse medial sampling, a close approximation of individual objects is achieved.
Mapping textured images on smoothly approximated surfaces is often used to conceal the loss of their real, fine-grained relief. A limitation of mapping a fixed texture in such cases is that it will only be correct for...
详细信息
ISBN:
(纸本)0769512720
Mapping textured images on smoothly approximated surfaces is often used to conceal the loss of their real, fine-grained relief. A limitation of mapping a fixed texture in such cases is that it will only be correct for one viewing and one illumination direction. The presence of geometric surface details causes changes that simple foreshortening and global color scaling cannot model well. Hence, one would like to synthesize different textures for different viewing conditions. A texture model is presented that takes account of viewpoint dependent changes in texture appearance. It is highly compact and avoids copy-and-paste like repetitions. The model is learned from example images taken from different viewpoints. It supports texture synthesis for previously unseen conditions.
image inpainting involves filling in part of an image or video using information from the surrounding area. Applications include the restoration of damaged photographs and movies and the removal of selected objects. W...
详细信息
ISBN:
(纸本)0769512720
image inpainting involves filling in part of an image or video using information from the surrounding area. Applications include the restoration of damaged photographs and movies and the removal of selected objects. We introduce a class of automated methods for digital inpainting. The approach uses ideas from classical fluid dynamics to propagate isophote lines continuously from the exterior into the region to be inpainted. The main idea is to think of the image intensity as a 'stream function for a two-dimensional incompressible flow. The Laplacian of the image intensity plays the role of the vorticity of the fluid; it is transported into the region to be inpainted by a vector field defined by the stream function. The resulting algorithm is designed to continue isophotes while matching gradient vectors at the boundary of the inpainting region. The method is directly based on the Navier-Stokes equations for fluid dynamics, which has the immediate advantage of well-developed theoretical and numerical results. This is a new approach for introducing ideas from computational fluid dynamics into problems in computer vision and image analysis.
We present a robust method for matching point features across a set of images under full perspective projection. An expectation-maximization-like algorithm is developed to build an optimal potential match set (PMS) be...
详细信息
ISBN:
(纸本)0769512720
We present a robust method for matching point features across a set of images under full perspective projection. An expectation-maximization-like algorithm is developed to build an optimal potential match set (PMS) between each consecutive pair of views, by iteratively maximizing a heuristic objective function. All two-view matches are combined to form an M-view potential match set (MPMS) with a low contamination rate. Outliers in MPMS are removed incorporating the least-median-of-squares technique with projective reconstruction. The current work extends previous ones in two- or three-view matching, or under affine camera projection. Results on real imagery demonstrate the validity of the proposed method.
A neural network based on Wilson-Cowan oscillators is used to perform object recognition in a two-dimensional visual scene. The temporal correlation among groups of oscillating neurons is used as the main criterion to...
详细信息
A neural network based on Wilson-Cowan oscillators is used to perform object recognition in a two-dimensional visual scene. The temporal correlation among groups of oscillating neurons is used as the main criterion to solve the classic binding and segmentation problem. The network uses an original pattern of short-range lateral excitations among adjacent neurons to achieve the binding problem, and an external inhibitory global neuron to provide segmentation of multiple objects in the same visual scene. The latter may represent an "attention mechanism" from neurons at a higher hierarchical level. Simulations performed by using multiple idealized figures (up to 4-5) in the presence of noise suggest that the network can satisfactorily recognize objects in most cases. However, the threshold and time constant of the attention mechanism depend on the complexity (number of objects and level of noise) of the scene under examination. The present results may be useful to improve our understanding of how distributed activities are integrated in the neural system to form single object perceptions. In perspective, the proposed model may find in practical algorithms for object recognition.
Most current techniques for minutiae extraction in fingerprint images utilize complex preprocessing.and postprocessing. In this paper, we propose a new technique, based on the use of learned templates, which statistic...
详细信息
ISBN:
(纸本)0769512720
Most current techniques for minutiae extraction in fingerprint images utilize complex preprocessing.and postprocessing. In this paper, we propose a new technique, based on the use of learned templates, which statistically characterize the minutiae. Templates are teamed from examples by optimizing a criterion function using Lagrange's method. To detect the presence of minutiae in test images, templates are applied with appropriate orientations to the binary image only at selected potential minutia locations. Several performance measures, which evaluate the quality and quantity of extracted features and their impact on identification, are used to evaluate the significance of learned templates. The performance of the proposed approach is evaluated on two sets of fingerprint images: one is collected by an optical scanner and the other one is chosen from NIST special fingerprint database 4. The experimental results show that learned templates can improve both the features and the performance of the identification system.
暂无评论