Results 1  10
of
28
Robust parameter estimation in computer vision
 SIAM Reviews
, 1999
"... Abstract. Estimation techniques in computer vision applications must estimate accurate model parameters despite smallscale noise in the data, occasional largescale measurement errors (outliers), and measurements from multiple populations in the same data set. Increasingly, robust estimation techni ..."
Abstract

Cited by 130 (10 self)
 Add to MetaCart
Abstract. Estimation techniques in computer vision applications must estimate accurate model parameters despite smallscale noise in the data, occasional largescale measurement errors (outliers), and measurements from multiple populations in the same data set. Increasingly, robust estimation techniques, some borrowed from the statistics literature and others described in the computer vision literature, have been used in solving these parameter estimation problems. Ideally, these techniques should effectively ignore the outliers and measurements from other populations, treating them as outliers, when estimating the parameters of a single population. Two frequently used techniques are leastmedian of
Skeletal Parameter Estimation from Optical Motion Capture Data
, 2005
"... In this paper we present an algorithm for automatically estimating a subject’s skeletal structure from optical motion capture data. Our algorithm consists of a series of steps that cluster markers into segment groups, determine the topological connectivity between these groups, and locate the positi ..."
Abstract

Cited by 35 (0 self)
 Add to MetaCart
In this paper we present an algorithm for automatically estimating a subject’s skeletal structure from optical motion capture data. Our algorithm consists of a series of steps that cluster markers into segment groups, determine the topological connectivity between these groups, and locate the positions of their connecting joints. Our problem formulation makes use of fundamental distance constraints that must hold for markers attached to an articulated structure, and we solve the resulting systems using a combination of spectral clustering and nonlinear optimization. We have tested our algorithms using data from both passive and active optical motion capture devices. Our results show that the system works reliably even with as few as one or two markers on each segment. For data recorded from human subjects, the system determines the correct topology and qualitatively accurate structure. Tests with a mechanical calibration linkage demonstrate errors for inferred segment lengths on average of only two percent. We discuss applications of our methods for commercial human figure animation, and for identifying human or animal subjects based on their motion independent of marker placement or feature selection.
A Survey of SpatioTemporal Grouping Techniques
, 2002
"... Spatiotemporal segmentation of video sequences attempts to extract backgrounds and independent objects in the dynamic scenes captured in the sequences. It is an essential step of video analysis. It has important applications in video coding, video logging, indexing and retrieval, and more generally ..."
Abstract

Cited by 27 (0 self)
 Add to MetaCart
Spatiotemporal segmentation of video sequences attempts to extract backgrounds and independent objects in the dynamic scenes captured in the sequences. It is an essential step of video analysis. It has important applications in video coding, video logging, indexing and retrieval, and more generally in scene interpretation and video understanding. We classify spatiotemporal grouping techniques into three categories: (1) segmentation with spatial priority, (2) segmentation by trajectory grouping, and (3) joint spatial and temporal segmentation. The first category is the broadest, as it inherits the legacy techniques of image segmentation and motion segmentation. The other two categories place a higher priority on the accumulation of evidence along the temporal dimension and are more recent developments made feasible by the increased availability of computing power. For each category we provide a taxonomy of the techniques used to produce meaningful pixel groupings.
Uncertainty modeling and model selection for geometric inference
 IEEE Trans. Pattern Anal. Mach. Intell
, 2004
"... Abstract—We first investigate the meaning of “statistical methods ” for geometric inference based on image feature points. Tracing back the origin of feature uncertainty to image processing operations, we discuss the implications of asymptotic analysis in reference to “geometric fitting ” and “geome ..."
Abstract

Cited by 24 (3 self)
 Add to MetaCart
Abstract—We first investigate the meaning of “statistical methods ” for geometric inference based on image feature points. Tracing back the origin of feature uncertainty to image processing operations, we discuss the implications of asymptotic analysis in reference to “geometric fitting ” and “geometric model selection ” and point out that a correspondence exists between the standard statistical analysis and the geometric inference problem. Then, we derive the “geometric AIC ” and the “geometric MDL ” as counterparts of Akaike’s AIC and Rissanen’s MDL. We show by experiments that the two criteria have contrasting characteristics in detecting degeneracy. Index Terms—statistical method, feature point extraction, asymptotic evaluation, geometric AIC, geometric MDL. 1
Joint Feature Distributions for Image Correspondence
 In Proceedings of the 8th International Conference on Computer Vision
, 2001
"... We develop a probabilistic framework for feature based multiimage matching that explicitly models the joint distribution of corresponding feature positions across several images. Conditioning this distribution on feature positions in some of the images gives welllocalized distributions for their co ..."
Abstract

Cited by 14 (0 self)
 Add to MetaCart
We develop a probabilistic framework for feature based multiimage matching that explicitly models the joint distribution of corresponding feature positions across several images. Conditioning this distribution on feature positions in some of the images gives welllocalized distributions for their correspondents in the others, which directly guide the correspondence search. This general framework is explored here in the simplest case of Gaussian distributions over the direct sum (affine images) and the tensor product (perspective images) of the image coordinates. Under these parametrizations, the formalism becomes a probabilistic generalization of the theory of multiimage matching constraints. It gracefully handles the full range of geometric correspondence models, including illconditioned nearplanar ones intermediate between between full perspective and plane homographies. Small amounts of distortion and nonrigidity can also be tolerated. We develop the theory for any number of affi...
Multibody segmentation: Revisiting motion consistency
 In International Workshop on Vision and Modeling of Dynamic Scenes (with ECCV02
, 2002
"... Dynamic analysis of video sequences often relies on the segmentation of the sequence into regions of consistent motions. Approaching this problem requires a definition of which motions are regarded as consistent. Common approaches to motion segmentation usually group together points or image regions ..."
Abstract

Cited by 12 (2 self)
 Add to MetaCart
Dynamic analysis of video sequences often relies on the segmentation of the sequence into regions of consistent motions. Approaching this problem requires a definition of which motions are regarded as consistent. Common approaches to motion segmentation usually group together points or image regions that have the same motion between successive frames (where the same motion can be 2D, 3D, or nonrigid). In this paper we define a new type of motion consistency, which is based on temporal consistency of behaviors across multiple frames in the video sequence. Our definition of consistent “temporal behavior ” is expressed in terms of multiframe linear subspace constraints. This definition applies to 2D, 3D, and some nonrigid motions without requiring prior model selection. We further present a multiframe multibody segmentation algorithm which applies the new motion consistency constraint directly to image brightness measurements, without requiring prior correspondence estimation nor feature tracking.
Model selection for geometric inference
 Proc. 5th Asian Conf. Comput. Vision
, 2002
"... Contrasting “geometric fitting”, for which the noise level is taken as the asymptotic variable, with “statistical inference”, for which the number of observations is taken as the asymptotic variable, we give a new definition of the “geometric AIC ” and the “geometric MDL ” as the counterparts of Aka ..."
Abstract

Cited by 10 (3 self)
 Add to MetaCart
Contrasting “geometric fitting”, for which the noise level is taken as the asymptotic variable, with “statistical inference”, for which the number of observations is taken as the asymptotic variable, we give a new definition of the “geometric AIC ” and the “geometric MDL ” as the counterparts of Akaike’s AIC and Rissanen’s MDL. We discuss various theoretical and practical problems that emerge from our analysis. Finally, we experimentally show that the geometric AIC and the geometric MDL have very different characteristics. 1.
Detecting moving objects in airborne forward looking infrared sequences
 Machine Vision Applications Journal
, 2000
"... In this paper we propose a system that detects independently moving objects (IMOs) in forward looking infrared (FLIR) image sequences taken from an airborne, moving platform. Egomotion effects are removed through a robust multiscale affine image registration process. Consequently, areas with resi ..."
Abstract

Cited by 8 (0 self)
 Add to MetaCart
In this paper we propose a system that detects independently moving objects (IMOs) in forward looking infrared (FLIR) image sequences taken from an airborne, moving platform. Egomotion effects are removed through a robust multiscale affine image registration process. Consequently, areas with residual motion indicate object activity. These areas are detected, refined and selected using a Bayes ’ classifier. The remaining regions are clustered into pairs. Each pair represents an object’s front and rear end. Using motion and scene knowledge we estimate object pose and establish a regionofinterest (ROI) for each pair. Edge elements within each ROI are used to segment the convex cover containing the IMO. We show detailed results on real, complex, cluttered and noisy sequences. Moreover, we outline the integration of our robust system into a comprehensive automatic target recognition (ATR) and action classification system.
On the Reprojection of 3D and 2D Scenes Without Explicit Model Selection
 In: Proc. 6th European Conference on Computer Vision
, 2000
"... It is known that recovering projection matrices from planar con#gurations is ambiguous, thus, posing the problem of model selection  is the scene planar #2D# or nonplanar #3D#? For a 2D scene one would recover a homography matrix, whereas for a 3D scene one would recover the fundamental matrix o ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
It is known that recovering projection matrices from planar con#gurations is ambiguous, thus, posing the problem of model selection  is the scene planar #2D# or nonplanar #3D#? For a 2D scene one would recover a homography matrix, whereas for a 3D scene one would recover the fundamental matrix or trifocal tensor. The task of model selection is especially problematic when the scene is neither 2D nor 3D  for example a #thin" volume in space. In this paper we show that for certain tasks, such as reprojection, thereisno need to select a model. The ambiguity that arises froma2Dscene is orthogonal to the reprojection process, thus if one desires to use multilinear matching constraints for transferring points along a sequence of views it is possible to do so under any situation of 2D, 3D or #thin" volumes. 1 Introduction There are certain mathematical objects connected with multipleview analysis which include: #i# homography matrix #2D collineation#, and #ii# objects associated wi...
Model Selection for Two View Geometry: A Review
 Microsoft Research, USA, Microsoft Research
, 1998
"... . Computer vision often concerns the estimation of models of the world from visual input. Sometimes it is possible to fit several di#erent models or hypotheses to a set of data, the choice of which is usually left to the vision practitioner. This paper explores ways of automating the model selec ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
. Computer vision often concerns the estimation of models of the world from visual input. Sometimes it is possible to fit several di#erent models or hypotheses to a set of data, the choice of which is usually left to the vision practitioner. This paper explores ways of automating the model selection process, with specific emphasis on the least squares problem. The statistical literature is reviewed and it will become apparent that although no one method has yet been developed that will be generally useful for all computer vision problems, there do exist some useful partial solutions. Thus this paper is intended as a beginner's guide to model selection, highlighting the pertinent problem areas in model selection and illustrating them by the example of estimating two view geometry. 1 Introduction Robotic vision has its basis in geometric modeling of the world, and many vision algorithms attempt to estimate these geometric models from perceived data. Usually only one model is...