Results 1  10
of
10
Learning Flexible Sprites in Video Layers
 In CVPR
, 2001
"... We propose a technique for automatically learning layers of "flexible sprites"  probabilistic 2dimensional appearance maps and masks of moving, occluding objects. The model explains each input image as a layered composition of exible sprites. A variational expectation maximization algor ..."
Abstract

Cited by 158 (20 self)
 Add to MetaCart
We propose a technique for automatically learning layers of "flexible sprites"  probabilistic 2dimensional appearance maps and masks of moving, occluding objects. The model explains each input image as a layered composition of exible sprites. A variational expectation maximization algorithm is used to learn a mixture of sprites from a video sequence. For each input image, probabilistic inference is used to infer the sprite class, translation, mask values and pixel intensities (including obstructed pixels) in each layer. Exact inference is intractable, but we show how a variational inference technique can be used to process 320 &times; 240 images at 1 frame/second. The only inputs to the learning algorithm are the video sequence, the number of layers and the number of flexible sprites. We give results on several tasks, including summarizing a video sequence with sprites, pointandclick video stabilization, and pointandclick object removal.
Layer Extraction with a Bayesian model of shapes
, 2000
"... . This paper describes an automatic 3D surface modelling system that extracts dense 3D surfaces from uncalibrated video sequences. In order to extract this 3D model the scene is represented as a collection of layers and a new method for layer extraction is described. The new segmentation method ..."
Abstract

Cited by 12 (5 self)
 Add to MetaCart
. This paper describes an automatic 3D surface modelling system that extracts dense 3D surfaces from uncalibrated video sequences. In order to extract this 3D model the scene is represented as a collection of layers and a new method for layer extraction is described. The new segmentation method diers from previous methods in that it uses a specic prior model for layer shape. A probabilistic hierarchical model of layer shape is constructed, which assigns a density function to the shape and spatial relationships between layers. This allows accurate and ecient algorithms to be used when nding the best segmentation. Here this framework is applied to architectural scenes, in which layers commonly correspond to windows or doors and hence belong to a tightly constrained family of shapes. Keywords: Structure from motion, Grouping and segmentation. 1 Introduction The aim of this work is to obtain dense 3D structure and texture maps from an image sequence, the camera matrices (c...
Mixture models for image representation
, 1996
"... We consider the estimation of local greylevel image structure in terms of a layered representation. This type of representation has recently been successfully used to segment various objects from clutter using either optical ow or stereo disparity information. We argue that the same type of represe ..."
Abstract

Cited by 9 (1 self)
 Add to MetaCart
(Show Context)
We consider the estimation of local greylevel image structure in terms of a layered representation. This type of representation has recently been successfully used to segment various objects from clutter using either optical ow or stereo disparity information. We argue that the same type of representation is useful for greylevel data in that it allows for the estimation of properties for each of several different components without prior segmentation. Our emphasis in this paper is on the process used to extract such a layered representation from a given image. In particular, we consider a variant of the EMalgorithm for the estimation of the layered model, and consider a novel technique for choosing the number of layers to use. We briefly consider the use of a simple version of this approach for image segmentation, and suggest two potential applications to the ARK project.
Monocular Perception of Biological Motion in Johansson Displays
 Computer Vision and Image Understanding
, 2001
"... this paper was partially published in the Proceedings of ICCV'99 and in the Proceedings of ECCV'00 ######## Computer perception of biological motion is key to developing convenient and powerful humancomputer interfaces. Algorithms have been developed for tracking the body; however, init ..."
Abstract

Cited by 6 (2 self)
 Add to MetaCart
(Show Context)
this paper was partially published in the Proceedings of ICCV'99 and in the Proceedings of ECCV'00 ######## Computer perception of biological motion is key to developing convenient and powerful humancomputer interfaces. Algorithms have been developed for tracking the body; however, initialization is done by hand. We propose a method for detecting a moving human body and for labeling its parts automatically in scenes that include extraneous motions and occlusion. We assume a Johansson display, i.e. that a number of moving features, some representing the unoccluded body joints and some belonging to the background are supplied in the scene. Our method is based on maximizing the joint probability density function (PDF) of the position and velocity of the body parts. The PDF is estimated from training data. Dynamic programming is used for calculating eciently the best global labeling on an approximation of the PDF. Detection is performed by hypothesis testing on the best labeling found. The computational cost is on the order of # where N is the number of features detected
Multiple Motion Analysis Using 3D Orientation Steerable Filters
, 2000
"... In this paper, we study the characterization of multiple motions from the standpoint of orientation in spatiotemporal volume. Using the fact that multiple motions are equivalent to multiple planes in the derivative space or in the spectral domain, we apply a new 3D steerable filter for motion estima ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
In this paper, we study the characterization of multiple motions from the standpoint of orientation in spatiotemporal volume. Using the fact that multiple motions are equivalent to multiple planes in the derivative space or in the spectral domain, we apply a new 3D steerable filter for motion estimation. This new method is based on the decomposition of the sphere with a set of overlapping basis filters in the feature space. It is superior to principal axis analysis based approaches and current 3D steerability approaches in achieving higher orientation resolution. Our approach is more efficient and robust than a similar spatiotemporal Hough transform and outperforms existing EM algorithms applied in the derivative space. In occlusion estimation,...
Eliminating Outliers in Motion Occlusion Analysis
 IN DAGM SYMPOSIUM MUSTERERKENNUNG
"... Occlusion boundaries are considered either as outliers or as noise in most optical ow algorithms. In order to treat the boundary problem, many probabilistic algorithms like maximum likelihood [6] or expectationmaximization (EM) [16, 3] are proposed to gradually decrease the weights of pixels in ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
Occlusion boundaries are considered either as outliers or as noise in most optical ow algorithms. In order to treat the boundary problem, many probabilistic algorithms like maximum likelihood [6] or expectationmaximization (EM) [16, 3] are proposed to gradually decrease the weights of pixels in boundary regions during estimation iterations. However,
Oscar Nestares
"... This chapter addresses an open problem in visual motion analysis, the estimation of image motion in the vicinity of occlusion boundaries. With a Bayesian formulation, local image motion is explained in terms of multiple, competing, nonlinear models, including models for smooth (translational) motion ..."
Abstract
 Add to MetaCart
(Show Context)
This chapter addresses an open problem in visual motion analysis, the estimation of image motion in the vicinity of occlusion boundaries. With a Bayesian formulation, local image motion is explained in terms of multiple, competing, nonlinear models, including models for smooth (translational) motion and for motion boundaries. The generative model for motion boundaries explicitly encodes the orientation of the boundary, the velocities on either side, the motion of the occluding edge over time, and the appearance/disappearance of pixels at the boundary. We formulate the posterior probability distribution over the models and model parameters, conditioned on the image sequence. Approximate inference is achieved with a combination of tools: A Bayesian lter provides for online computation; factored sampling allows us to represent multimodal nonGaussian distributions and to propagate beliefs with nonlinear dynamics from one time to the next; and mixture models are used to simplify the computation of joint prediction distributions in the Bayesian lter. To eĆciently represent such
1On Optical Flow
"... The measurement of optical
ow is a fundamental problem in Computer Vision. Many techniques have been presented in the literature and many more continue to appear. How would one select an appropriate method for a given task? We overview the various classes of optical
ow methods and describe example ..."
Abstract
 Add to MetaCart
The measurement of optical
ow is a fundamental problem in Computer Vision. Many techniques have been presented in the literature and many more continue to appear. How would one select an appropriate method for a given task? We overview the various classes of optical
ow methods and describe examples of each, emphasizing both the advantages and drawbacks of each class of methods. We conclude the paper with an example of optical ow as a tool for measuring the growth of corn seedlings. 1
1The Computation of Optical Flow
"... Twodimensional image motion is the projection of the threedimensional motion of objects, relative to a visual sensor, onto its image plane. Sequences of timeordered images allow the estimation of projected twodimensional image motion as either instantaneous image velocities or discrete image dis ..."
Abstract
 Add to MetaCart
(Show Context)
Twodimensional image motion is the projection of the threedimensional motion of objects, relative to a visual sensor, onto its image plane. Sequences of timeordered images allow the estimation of projected twodimensional image motion as either instantaneous image velocities or discrete image displacements. These are usually called the optical
ow eld or the image velocity eld. Provided that optical
ow is a reliable approximation to twodimensional image motion, it may then be used to recover the threedimensional motion of the visual sensor (to within a scale factor) and the threedimensional surface structure (shape or relative depth) through assumptions concerning the structure of the optical
ow eld, the threedimensional environment and the motion of the sensor. Optical
ow may also be used to perform motion detection, object segmentation, timetocollision and focus of expansion calculations, motion compensated encoding and stereo disparity measurement. We investigate the computation of optical
ow in this survey: widely known methods for estimating optical
ow are classied and examined by scrutinizing the hypotheses and
Motion Segmentation Across Image Sequences
, 2001
"... This thesis was submitted to the University of Bristol in accordance with the ..."
Abstract
 Add to MetaCart
This thesis was submitted to the University of Bristol in accordance with the