Results 1  10
of
58
Recognizing Objects in Range Data Using Regional Point Descriptors
 EUROPEAN CONFERENCE ON COMPUTER VISION
, 2004
"... Recognition of three dimensional (3D) objects in noisy and cluttered scenes is a challenging problem in 3D computer vision. One approach that has been successful in past research is the regional shape descriptor. In this paper, we introduce two new regional shape descriptors: 3D shape contexts a ..."
Abstract

Cited by 206 (8 self)
 Add to MetaCart
(Show Context)
Recognition of three dimensional (3D) objects in noisy and cluttered scenes is a challenging problem in 3D computer vision. One approach that has been successful in past research is the regional shape descriptor. In this paper, we introduce two new regional shape descriptors: 3D shape contexts and harmonic shape contexts. We evaluate the performance of these descriptors on the task of recognizing vehicles in range scans of scenes using a database of 56 cars. We compare the two novel descriptors to an existing descriptor, the spin image, showing that the shape context based descriptors have a higher recognition rate on noisy scenes and that 3D shape contexts outperform the others on cluttered scenes.
Computing Optical Flow with Physical Models of Brightness Variation
"... This paper exploits physical models of timevarying brightness in image sequences to estimate optical flow and physical parameters of the scene. Previous approaches handled violations of brightness constancy with the use of robust statistics or with generalized brightness constancy constraints that ..."
Abstract

Cited by 101 (1 self)
 Add to MetaCart
This paper exploits physical models of timevarying brightness in image sequences to estimate optical flow and physical parameters of the scene. Previous approaches handled violations of brightness constancy with the use of robust statistics or with generalized brightness constancy constraints that allow generic types of contrast and illumination changes. Here, we consider models of brightness variation that have timedependent physical causes, namely, changing surface orientation with respect to a directional illuminant, motion of the illuminant, and physical models of heat transport in infrared images. We simultaneously estimate the optical flow and the relevant physical parameters. The estimation problem is formulated using total least squares (TLS), with confidence bounds on the parameters.
On the fitting of surfaces to data with covariances
 IEEE Trans. Patt. Anal. Mach. Intell
, 2000
"... AbstractÐWe consider the problem of estimating parameters of a model described by an equation of special form. Specific models arise in the analysis of a wide class of computer vision problems, including conic fitting and estimation of the fundamental matrix. We assume that noisy data are accompanie ..."
Abstract

Cited by 75 (19 self)
 Add to MetaCart
(Show Context)
AbstractÐWe consider the problem of estimating parameters of a model described by an equation of special form. Specific models arise in the analysis of a wide class of computer vision problems, including conic fitting and estimation of the fundamental matrix. We assume that noisy data are accompanied by (known) covariance matrices characterizing the uncertainty of the measurements. A cost function is first obtained by considering a maximumlikelihood formulation and applying certain necessary approximations that render the problem tractable. A novel, Newtonlike iterative scheme is then generated for determining a minimizer of the cost function. Unlike alternative approaches such as Sampson's method or the renormalization technique, the new scheme has as its theoretical limit the minimizer of the cost function. Furthermore, the scheme is simply expressed, efficient, and unsurpassed as a general technique in our testing. An important feature of the method is that it can serve as a basis for conducting theoretical comparison of various estimation approaches.
Point Matching under Large Image Deformations and Illumination Changes
 IEEE TRANS. PATTERN ANAL. MACHINE INTELL
, 2004
"... To solve the general point correspondence problem in which the underlying transformation between image patches is represented by a homography, a solution based on extensive use of first order differential techniques is proposed. We integrate in a single robust Mestimation framework the traditiona ..."
Abstract

Cited by 50 (9 self)
 Add to MetaCart
To solve the general point correspondence problem in which the underlying transformation between image patches is represented by a homography, a solution based on extensive use of first order differential techniques is proposed. We integrate in a single robust Mestimation framework the traditional optical flow method and matching of local color distributions. These distributions are computed with spatially oriented kernels in the 5D joint spatial/color space. The estimation process is initiated at the third level of a Gaussian pyramid, uses only local information, and the illumination changes between the two images are also taken into account. Subpixel
Scalable Extrinsic Calibration of OmniDirectional Image Networks
 International Journal of Computer Vision
, 2002
"... We describe a lineartime algorithm that recovers absolute camera orientations and positions, along with uncertainty estimates, for networks of terrestrial image nodes spanning hundreds of meters in outdoor urban scenes. The algorithm produces pose estimates globally consistent to roughly 0.1 # (2 ..."
Abstract

Cited by 46 (6 self)
 Add to MetaCart
We describe a lineartime algorithm that recovers absolute camera orientations and positions, along with uncertainty estimates, for networks of terrestrial image nodes spanning hundreds of meters in outdoor urban scenes. The algorithm produces pose estimates globally consistent to roughly 0.1 # (2 milliradians) and 5 centimeters on average, or about four pixels of epipolar alignment.
Building blocks for hierarchical latent variable models
 In In Proceedings of the 3rd International Conference on Independent Component Analysis and Blind Signal Separation
, 2006
"... Abstract—We propose a new method for rapid 3D object indexing that combines featurebased methods with coarse alignmentbased matching techniques. Our approach achieves a sublinear complexity on the number of models, maintaining at the same time a high degree of performance for real 3D sensed data t ..."
Abstract

Cited by 36 (1 self)
 Add to MetaCart
Abstract—We propose a new method for rapid 3D object indexing that combines featurebased methods with coarse alignmentbased matching techniques. Our approach achieves a sublinear complexity on the number of models, maintaining at the same time a high degree of performance for real 3D sensed data that is acquired in largely uncontrolled settings. The key component of our method is to first index surface descriptors computed at salient locations from the scene into the whole model database using the Locality Sensitive Hashing (LSH), a probabilistic approximate nearest neighbor method. Progressively complex geometric constraints are subsequently enforced to further prune the initial candidates and eliminate false correspondences due to inaccuracies in the surface descriptors and the errors of the LSH algorithm. The indexed models are selected based on the MAP rule using posterior probability of the models estimated in the joint 3Dsignature space. Experiments with real 3D data employing a large database of vehicles, most of them very similar in shape, containing 1,000,000 features from more than 365 models demonstrate a high degree of performance in the presence of occlusion and obscuration, unmodeled vehicle interiors and part articulations, with an average processing time between 50 and 100 seconds per query. Index Terms—Threedimensional object recognition, hashing, indexing, pose estimation, approximate nearest neighbor. Ç
Estimation of nonlinear errorsinvariables models for computer vision applications
 IEEE Trans. Patt. Anal. Mach. Intell
, 2006
"... Abstract—In an errorsinvariables (EIV) model, all the measurements are corrupted by noise. The class of EIV models with constraints separable into the product of two nonlinear functions, one solely in the variables and one solely in the parameters, is general enough to represent most computer visi ..."
Abstract

Cited by 33 (6 self)
 Add to MetaCart
(Show Context)
Abstract—In an errorsinvariables (EIV) model, all the measurements are corrupted by noise. The class of EIV models with constraints separable into the product of two nonlinear functions, one solely in the variables and one solely in the parameters, is general enough to represent most computer vision problems. We show that the estimation of such nonlinear EIV models can be reduced to iteratively estimating a linear model having point dependent, i.e., heteroscedastic, noise process. Particular cases of the proposed heteroscedastic errorsinvariables (HEIV) estimator are related to other techniques described in the vision literature: the Sampson method, renormalization, and the fundamental numerical scheme. In a wide variety of tasks, the HEIV estimator exhibits the same, or superior, performance as these techniques and has a weaker dependence on the quality of the initial solution than the LevenbergMarquardt method, the standard approach toward estimating nonlinear models. Index Terms—Nonlinear least squares, heteroscedastic regression, camera calibration, 3D rigid motion, uncalibrated vision. 1 MODELING COMPUTER VISION PROBLEMS SOLVING most computer vision problems requires the estimation of a set of parameters from noisy measurements using a statistical model. A statistical model provides a mathematical description of a problem in terms of a constraint equation relating the measurements to the
From FNS to HEIV: A Link between Two Vision Parameter Estimation Methods
 IEEE Trans. Pattern Anal. Mach. Intell
, 2004
"... Abstract — Problems requiring accurate determination of parameters from imagebased quantities arise often in computer vision. Two recent, independently developed frameworks for estimating such parameters are the FNS and HEIV schemes. Here, it is shown that FNS and a core version of HEIV are essenti ..."
Abstract

Cited by 20 (4 self)
 Add to MetaCart
(Show Context)
Abstract — Problems requiring accurate determination of parameters from imagebased quantities arise often in computer vision. Two recent, independently developed frameworks for estimating such parameters are the FNS and HEIV schemes. Here, it is shown that FNS and a core version of HEIV are essentially equivalent, solving a common underlying equation via different means. The analysis is driven by the search for a nondegenerate form of a certain generalized eigenvalue problem, and effectively leads to a new derivation of the relevant case of the HEIV algorithm. This work may be seen as an extension of previous efforts to rationalize and interrelate a spectrum of estimators, including the renormalization method of Kanatani and the normalized eightpoint method of Hartley. Index Terms — Statistical methods, maximum likelihood, (un)constrained minimization, fundamental matrix, epipolar equation I.
A New Constrained Parameter Estimator For Computer Vision Applications
"... Previous work of the authors developed a theoretically wellfounded scheme (FNS) for finding the minimiser of a class of cost functions. Various problems in video analysis, stereo vision, ellipsefitting, etc, may be expressed in terms of finding such a minimiser. However, in common with many other ..."
Abstract

Cited by 18 (4 self)
 Add to MetaCart
Previous work of the authors developed a theoretically wellfounded scheme (FNS) for finding the minimiser of a class of cost functions. Various problems in video analysis, stereo vision, ellipsefitting, etc, may be expressed in terms of finding such a minimiser. However, in common with many other approaches, it is necessary to correct the minimiser as a postprocess if an ancillary constraint is also to be satisfied. In this paper we develop the first integrated scheme (CFNS) for simultaneously minimising the cost function and satisfying the constraint. Preliminary experiments in the domain of fundamentalmatrix estimation show that CFNS generates rank2 estimates with smaller cost function values than rank2 corrected FNS estimates. Furthermore, when compared with the HartleyZisserman Gold Standard method, CFNS is seen to generate results of comparable quality in a fraction of the time.
Scalable, Absolute Position Recovery for OmniDirectional Image Networks
 In Proc. CVPR
, 2001
"... We describe a lineartime algorithm that recovers absolute camera positions for networks of thousands of terrestrial images spanning hundreds of meters, in outdoor urban scenes, under varying lighting conditions. The algorithm requires no human input or interaction. It is robust to up to 80% outlier ..."
Abstract

Cited by 14 (2 self)
 Add to MetaCart
(Show Context)
We describe a lineartime algorithm that recovers absolute camera positions for networks of thousands of terrestrial images spanning hundreds of meters, in outdoor urban scenes, under varying lighting conditions. The algorithm requires no human input or interaction. It is robust to up to 80% outliers for synthetic data. For real data, it recovers camera pose which is globally consistent on average to roughly 0.1 # and five centimeters, or about four pixels of epipolar alignment, expending a few CPUhours of computation on a 250MHz processor. This paper's principal contributions include an extension of Monte Carlo Markov Chain estimation techniques to the case of unknown numbers of feature points, unknown occlusion and deocclusion, and large scale (thousands of images, and hundreds of thousands of point features) and dimensional extent (tens of meters of intercamera baseline, and hundreds of meters of baseline overall). Also, a principled method is given to manage uncertainty on the sphere of directions; a new use of the Hough Transform is proposed; and a method for aggregating local baseline constraints into a globally consistent constraint set is described. The algorithm takes intrinsic calibration information, and a connected, rotationally registered image network as input. It then assembles local, purely translational motion estimates into a global constraint set, and determines camera positions with respect to a single scenewide coordinate system. The algorithm's output is an assignment of metric, accurate 6DOF camera pose, along with its uncertainty, to every image. We assume that the scene exhibits local point features for probabilistic matching, and that adjacent cameras observe overlapping portions of the scene; no further assumptions are made about scene str...