# Proceedings of the Seventh IEEE International Conference on Computer Vision

## Filter Results

Displaying Results 1 - 25 of 81
• ### Index of authors

Publication Year: 1999, Page(s):xxiv - xxvii
| PDF (230 KB)
• ### Control in a 3D reconstruction system using selective perception

Publication Year: 1999, Page(s):1229 - 1236 vol.2
Cited by:  Papers (1)
| | PDF (240 KB)

This paper presents a control structure for general purpose image understanding that addresses both the high level of uncertainty in local hypotheses and the computational complexity of image interpretation. The control of vision algorithms is performed by an independent subsystem that uses Bayesian networks and utility theory to compute the marginal value of information provided by alternative op... View full abstract»

• ### A pattern classification approach to dynamical object detection

Publication Year: 1999, Page(s):1223 - 1228 vol.2
Cited by:  Papers (10)  |  Patents (3)
| | PDF (184 KB)

Current systems for object detection in video sequences rely on explicit dynamical models like Kalman filters or hidden Markov models. There is significant overhead needed in the development of such systems as well as the a priori assumption that the object dynamics can be described with such a dynamical model. This paper describes a new pattern classification technique for object detection in vid... View full abstract»

• ### Learning and evaluating visual features for pose estimation

Publication Year: 1999, Page(s):1217 - 1222 vol.2
Cited by:  Papers (26)
| | PDF (204 KB)

We present a method for learning a set of visual landmarks which are useful for pose estimation. The landmark learning mechanism is designed to be applicable to a wide range of environments, and generalized for different approaches to computing a pose estimate. Initially, each landmark is detected as a focal extremum of a measure of distinctiveness and represented by a principal components encodin... View full abstract»

• ### Learning-based object detection in cardiac MR images

Publication Year: 1999, Page(s):1210 - 1216 vol.2
Cited by:  Papers (1)  |  Patents (4)
| | PDF (568 KB)

An automated method for left ventricle detection in MR cardiac images is presented. Ventricle detection is the first step in a fully automated segmentation system used to compute volumetric information about the heart. Our method is based on learning the gray level appearance of the ventricle by maximizing the discrimination between positive and negative examples in a training set. The main differ... View full abstract»

• ### Segmentation of salient closed contours from real images

Publication Year: 1999, Page(s):891 - 897 vol.2
Cited by:  Papers (12)  |  Patents (2)
| | PDF (224 KB)

Using a saliency measure based on the global property of contour closure, we have developed a method that reliably segments out salient contours bounding unknown objects from real edge images. The measure also incorporates the Gestalt principles of proximity and smooth continuity that previous methods have exploited. Unlike previous measures, we incorporate contour closure by finding the eigen-sol... View full abstract»

• ### Modeling Bayesian estimation for deformable contours

Publication Year: 1999, Page(s):991 - 996 vol.2
Cited by:  Papers (8)
| | PDF (220 KB)

A novel trainable snake model called EigenSnake, is presented in the Bayesian framework. In the EigenSnake, prior knowledge of a specific object shape, such as that of face outlines and facial features, is derived from a training set of the shape and incorporated into a Bayesian snake model in the form of the prior distribution. Further, a “shape space”, which is constructed on the bas... View full abstract»

• ### Recognizing surfaces using three-dimensional textons

Publication Year: 1999, Page(s):1010 - 1017 vol.2
Cited by:  Papers (63)
| | PDF (208 KB)

We study the recognition of surfaces made from different materials such as concrete, rug, marble or leather on the basis of their textural appearance. Such natural textures arise from spatial variation of two surface attributes: (1) reflectance and (2) surface normal. In this paper, we provide a unified model to address both these aspects of natural texture. The main idea is to construct a vocabul... View full abstract»

• ### Error detection and DEM fusion using self-consistency

Publication Year: 1999, Page(s):1174 - 1181 vol.2
Cited by:  Papers (12)  |  Patents (1)
| | PDF (4904 KB)

The ability to efficiently and robustly recover accurate 3D terrain models from sets of stereoscopic images is important to many civilian and military applications. Our long-term goal is to develop an automatic, multi-image 3D reconstruction algorithm that can be applied to these domains. To develop an effective and practical terrain modeling system, methods must be found for detecting unreliable ... View full abstract»

• ### Polarization-based decorrelation of transparent layers: The inclination angle of an invisible surface

Publication Year: 1999, Page(s):814 - 819 vol.2
Cited by:  Papers (36)
| | PDF (196 KB)

When a transparent surface is present between an observer and an object, an image reflected by the surface may be superimposed on the image of the observed object. We present a new approach to recover the scenes (layers) and to classify which is the reflected/transmitted one, based on imaging through a polarizing filter at two orientations. Estimates of the separate layers are obtained by weighted... View full abstract»

• ### Finding correspondences of patches by means of affine transformations

Publication Year: 1999, Page(s):1117 - 1122 vol.2
| | PDF (184 KB)

We present a novel method for finding the optimal affine transformation for matching of images. The method requires no feature points, does not rely on normalization of images and can be tuned to highlight interesting parts in the images. Furthermore, the method does not need any derivatives for obtaining the affine transformation and it has a computational cost proportional to n2logn f... View full abstract»

• ### Higher order statistical learning for vehicle detection in images

Publication Year: 1999, Page(s):1204 - 1209 vol.2
Cited by:  Papers (24)
| | PDF (336 KB)

The paper describes a scheme for detecting vehicles in images. The proposed method approximately models the unknown distribution of the images of vehicles by learning higher order statistics (HOS) information of the vehicle class' from sample images. Given a test image, statistical information about the background is learnt on the fly'. An HOS-based decision measure then classifies test patterns... View full abstract»

• ### Subpixel-precise extraction of watersheds

Publication Year: 1999, Page(s):884 - 890 vol.2
Cited by:  Papers (10)
| | PDF (432 KB)

An approach to extract watersheds and watercourses, as well as their corresponding valleys and hills, from images with subpixel precision is proposed. The critical points of the terrain are essential as the starting points for the construction of these separatrices. They are extracted efficiently with subpixel precision using an approach based on derivatives of Gaussian filters. The separatrices a... View full abstract»

• ### Geodesic active regions for supervised texture segmentation

Publication Year: 1999, Page(s):926 - 932 vol.2
Cited by:  Papers (60)  |  Patents (2)
| | PDF (312 KB)

The paper presents a novel variational method for supervised texture segmentation. The textured feature space is generated by filtering the given textured images using isotropic and anisotropic filters, and analyzing their responses as multi-component conditional probability density functions. The texture segmentation is obtained by unifying region and boundary based information as an improved Geo... View full abstract»

• ### Estimation of diffuse and specular appearance

Publication Year: 1999, Page(s):855 - 860 vol.2
Cited by:  Papers (18)
| | PDF (148 KB)

To account for the variability of object appearance due to differences in illumination, attention has recently been focused on representing the set of images for all possible lighting conditions. Approaches that address this problem have primarily focused on lighting differences for diffuse reflection using the Lambertian model; however specular reflections can additionally present considerable di... View full abstract»

• ### Curve finder combining perceptual grouping and a Kalman like fitting

Publication Year: 1999, Page(s):1003 - 1008 vol.2
Cited by:  Papers (11)  |  Patents (2)
| | PDF (136 KB)

We present an algorithm that extracts curves from a set of edgels within a specific class in a decreasing order of their “length”. The algorithm inherits the perceptual grouping approaches. But, instead of using only local cues, a global constraint is imposed on each extracted subset of edgels, that the underlying curve belongs to a specific class. In order to reduce the complexity of ... View full abstract»

• ### The Earth Mover's Distance under transformation sets

Publication Year: 1999, Page(s):1076 - 1083 vol.2
Cited by:  Papers (34)  |  Patents (1)
| | PDF (316 KB)

The Earth Mover's Distance (EMD) is a distance measure between distributions with applications in image retrieval and matching. We consider the problem of computing a transformation of one distribution which minimizes its EMD to another. The applications discussed here include estimation of the size at which a color pattern occurs in an image, lighting-invariant object recognition, and point featu... View full abstract»

• ### Object localization by Bayesian correlation

Publication Year: 1999, Page(s):1068 - 1075 vol.2
Cited by:  Papers (53)  |  Patents (4)
| | PDF (636 KB)

Maximisation of cross correlation is a commonly used principle for intensity based object localization that gives a single estimate of location. However, to facilitate sequential inference (e.g. over time or scale) and to allow the representation of ambiguity, it is desirable to represent an entire probability distribution for object location. Although the cross correlation itself (or some functio... View full abstract»

• ### Registration of multiple point sets using the EM algorithm

Publication Year: 1999, Page(s):730 - 736 vol.2
Cited by:  Papers (6)
| | PDF (288 KB)

We address the problem of global registration between multiple d-dimensional point patterns with a given correspondence. The actual overlapping is not necessarily between pairs. Instead, it can be between any number of patterns. It is assumed that each pattern is a portion of an image of an unobserved object under a distinct rigid transformation. We derive an iterative solution for the problem of ... View full abstract»

• ### A cluster-based statistical model for object detection

Publication Year: 1999, Page(s):1046 - 1053 vol.2
Cited by:  Papers (17)  |  Patents (1)
| | PDF (288 KB)

This paper presents an approach to object detection which is based on recent work in statistical models for texture synthesis and recognition. Our method follows the texture recognition work of De Bonet and Viola (1998). We use feature vectors which capture the joint occurrence of local features at multiple resolutions. The distribution of feature vectors for a set of training images of an object ... View full abstract»

• ### Empirical evaluation of dissimilarity measures for color and texture

Publication Year: 1999, Page(s):1165 - 1172 vol.2
Cited by:  Papers (99)  |  Patents (3)
| | PDF (592 KB)

This paper empirically compares nine image dissimilarity measures that are based on distributions of color and texture features summarizing over 1,000 CPU hours of computational experiments. Ground truth is collected via a novel random sampling scheme for color and via an image partitioning method for texture. Quantitative performance evaluations are given for classification, image retrieval, and ... View full abstract»

• ### Monocular perception of biological motion-detection and labeling

Publication Year: 1999, Page(s):805 - 812 vol.2
Cited by:  Papers (8)  |  Patents (1)
| | PDF (208 KB)

Computer perception of biological motion is key to developing convenient and powerful human-computer interfaces. Successful body tracking algorithms have been developed; however initialization is done by hand. We propose a method for detecting a moving human body and for labeling its parts automatically. It is based on maximizing the joint probability density function (PDF) of the position and vel... View full abstract»

• ### Semantic organization of scenes using discriminant structural templates

Publication Year: 1999, Page(s):1253 - 1258 vol.2
Cited by:  Papers (14)  |  Patents (3)
| | PDF (152 KB)

In this paper, we present a procedure for organizing real world scenes along semantic axes. The approach is based on the output energies of linear discriminant filters that take into account, or not, spatial information. We introduce three semantic axes along which pictures are ordered. The main semantic axis computes the degree of naturalness of a scene. Then, urban pictures are evaluated accordi... View full abstract»

• ### Utilizing scatter for pixel subspace selection

Publication Year: 1999, Page(s):1111 - 1116 vol.2
Cited by:  Papers (2)  |  Patents (2)
| | PDF (244 KB)

Measures of scatter are used in statistical pattern recognition to identify and select important features, computed as linear combinations of the given features. Examples include principal components and linear discriminants. The classic computational procedures require eigenvector decomposition of large matrices, and in the case of images they are only practical for identifying a low dimensional ... View full abstract»

• ### Accurate motion flow estimation with discontinuities

Publication Year: 1999, Page(s):695 - 702 vol.2
Cited by:  Papers (8)  |  Patents (1)
| | PDF (200 KB)

We address the problem of motion flow estimation for a scene with multiple moving objects, observed from a possibly moving camera. We take as input a (possibly sparse) noisy velocity field, as obtained from local matching, produce a set of motion boundaries, and identify pixels with different velocities in overlapping layers. For a fixed observer, these overlapping layers capture occlusion informa... View full abstract»