Given a collection of images (matrices) representing a "class" of objects we present a method for extracting the commonalities of the image space directly from the matrix representations (rather than from th...
详细信息
ISBN:
(纸本)0769512720
Given a collection of images (matrices) representing a "class" of objects we present a method for extracting the commonalities of the image space directly from the matrix representations (rather than from the vectorized representation which one would normally do in a PCA approach, for example). The general idea is to consider the collection of matrices as a tensor and to look for an approximation of its tensor-rank. The tensor-rank approximation is designed such that the SVD decomposition emerges in the special case where all the input matrices are the repeatition of a single matrix. We evaluate the coding technique both in terms of regression, i.e., the efficiency of the technique for functional approximation, and classification. We find that for regression the tensor-rank coding, as a dimensionality reduction technique, significantly outperforms other techniques like PCA. As for classification, the tensor-rank coding is at is best when the number of training examples is very small.
We explore the geometry linking the shape of a curved mirror surface to the distortions it produces on a scene it reflects. Our analysis is local and differential. We assume a simple calibrated scene composed of lines...
详细信息
ISBN:
(纸本)0769512720
We explore the geometry linking the shape of a curved mirror surface to the distortions it produces on a scene it reflects. Our analysis is local and differential. We assume a simple calibrated scene composed of lines passing through a point. We demonstrate that local information about the geometry of the surface may be recovered up to the second order from either the orientation and curvature of the images of two intersecting lines, or from the orientation of the images of three or more intersecting lines. An explicit solution for calculating shape and position of spherical mirror surfaces is given.
Video segmentation is different from segmentation of a single image. While several correct solutions may exist for segmenting a single image, there needs to be a consistency among segmentations of each frame for video...
详细信息
ISBN:
(纸本)0769512720
Video segmentation is different from segmentation of a single image. While several correct solutions may exist for segmenting a single image, there needs to be a consistency among segmentations of each frame for video segmentation. Previous approaches of video segmentation concentrate on motion, or combine motion and color information in a batch fashion. We propose a maximum a posteriori probability (MAP) framework that uses multiple cues, like spatial location, color and motion, for segmentation. We assign weights to color and motion terms, which are adjusted at every pixel, based on a confidence measure of each feature. We also discuss the appropriate modeling of pdfs of each feature of a region. The correct modeling of the spatial pdf imposes temporal consistency among segments in consecutive frames. This approach unifies the strengths of both color segmentation and motion segmentation in one framework, and shows good results on videos that are not suited for either of these approaches.
This paper concerns the segmentation of successive frames of a video sequence. Traditional methods, treating each frame in isolation, are computationally expensive, ignore potentially useful information derived from p...
详细信息
ISBN:
(纸本)0769512720
This paper concerns the segmentation of successive frames of a video sequence. Traditional methods, treating each frame in isolation, are computationally expensive, ignore potentially useful information derived from previous frames, and can lead to instabilities over the sequence. The approach developed here, based on the Region Competition algorithm (Zhu and Yuille, ieee Trans. PAMI, 1996), employs a mesh of active contour primitives supervised by an MDL energy criterion. Temporal extensions, namely Boundary Momentum, Region Memory, and Optical Boundary Flow, are developed to ease the transition between successive frames. Further enhancements are made by incorporating mechanisms to accommodate the topological discontinuities that can arise during the sequence. The algorithm is demonstrated using a number of synthetic and real video sequences and is shown to provide an efficient method of segmentation which encourages stability across frames and preserves the quality of the original segmentation over the sequence.
In this paper, an iterative algorithm for auto-calibration is presented. The proposed algorithm switches between linearly estimating the dual of the absolute conic and the intrinsic parameters, while also incorporatin...
详细信息
ISBN:
(纸本)0769512720
In this paper, an iterative algorithm for auto-calibration is presented. The proposed algorithm switches between linearly estimating the dual of the absolute conic and the intrinsic parameters, while also incorporating the rank-3 constraint on the intrinsic parameters. The most important property of the algorithm is that it is completely general in the sense that any type of constraint on the intrinsic parameters might be used The proposed algorithm locates in-between of a non-linear optimization and initial linear computation, and provides robust and sufficiently accurate initial values for a bundle adjustment routine. The performance of the algorithm is shown for both simulated and real data, especially in the important case of natural (zero skew and unit aspect ratio) cameras.
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.
This work is concerned with the reconstruction of the original undistorted image of a curled document or book when captured face-up by a camera with the support of sparse depth measurements. A novel method based on ph...
详细信息
ISBN:
(纸本)0769512720
This work is concerned with the reconstruction of the original undistorted image of a curled document or book when captured face-up by a camera with the support of sparse depth measurements. A novel method based on physically modeling paper deformation with an applicable surface is proposed and a relaxation algorithm is described that allows us to fit it to noisy data and then flatten it in order to produce the final undistorted image. The promising results obtained confirm that the use of applicable surfaces is the right way to address this problem.
Segmenting and tracking multiple humans is a challenging problem in complex situations in which extended occlusion, shadow and/or reflection exists. We tackle this problem with a 3D model-based approach. Our method in...
详细信息
ISBN:
(纸本)0769512720
Segmenting and tracking multiple humans is a challenging problem in complex situations in which extended occlusion, shadow and/or reflection exists. We tackle this problem with a 3D model-based approach. Our method includes two stages, segmentation (detection) and tracking. Human hypotheses are generated by shape analysis of the foreground blobs using human shape model. The segmented human hypotheses are tracked with a Kalman filter with explicit handling of occlusion. Hypotheses are verified while they are tracked for the first second or so. The verification is done by walking recognition using an articulated human walking model. We propose a new method to recognize walking using motion template and temporal integration. Experiments show that our approach works robustly in very challenging sequences.
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 learned 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.
As panoramic photography becomes increasingly popular, there is a greater need for high-quality software to automatically create panoramic images. Existing algorithms either produce a rough "stitch" that can...
详细信息
ISBN:
(纸本)0769512720
As panoramic photography becomes increasingly popular, there is a greater need for high-quality software to automatically create panoramic images. Existing algorithms either produce a rough "stitch" that cannot deal with common artifacts, or require user input. This paper presents methods for dealing with two artifacts that often occur in practice. Our first contribution is a method for dealing with objects that move between different views of a dynamic scene. If such moving objects are left in, they will appear blurry and "ghosted". Treating such regions as nodes in a graph, we use a vertex cover algorithm to selectively remove all but one instance of-each object. Our second contribution is a method for continuously adjusting exposure across multiple images in order to eliminate visible shifts in brightness or hue. We compute exposure corrections on a block-by block basis, then smoothly interpolate the parameters using a spline to get spatially continuous exposure adjustment. Our enhancements, combined with previously published techniques for automatic image stitching, result in a high-quality automated stitcher that exhibits far fewer artifacts than existing software.
暂无评论