Hyperplane approximation for template matching

Jurie, Frédéric; Dhome, Michel

doi:10.1109/tpami.2002.1017625

Cited by 184 publications

(254 citation statements)

References 7 publications

Supporting

Mentioning

243

Contrasting

Unclassified

Order By: Relevance

“…Randomly generated training samples are also used in the iterative procedure, e.g. Hyperplane Approximation [13], which is similar in spirit to our approach. However, they use a spatially linear distortion model along with a linear estimator (hyperplane) that does not guarantee global optimality.…”

Section: Related Workmentioning

confidence: 99%

Globally Optimal Estimation of Nonrigid Image Distortion

Tian

Narasimhan

2011

Int J Comput Vis

View full text Add to dashboard Cite

Image alignment in the presence of non-rigid distortions is a challenging task. Typically, this involves estimating the parameters of a dense deformation field that warps a distorted image back to its undistorted template. Generative approaches based on parameter optimization such as Lucas-Kanade can get trapped within local minima. On the other hand, discriminative approaches like nearestneighbor require a large number of training samples that grows exponentially with respect to the dimension of the parameter space, and polynomially with the desired accuracy 1/ . In this work, we develop a novel data-driven iterative algorithm that combines the best of both generative and discriminative approaches. For this, we introduce the notion of a "pull-back" operation that enables us to predict the parameters of the test image using training samples that are not in its neighborhood (not -close) in the parameter space. We prove that our algorithm converges to the global optimum using a significantly lower number of training samples that grows only logarithmically with the desired accuracy. We analyze the behavior of our algorithm extensively using synthetic data and demonstrate successful results on experiments with complex deformations due to water and clothing.

show abstract

Section: Related Workmentioning

confidence: 99%

Globally Optimal Estimation of Nonrigid Image Distortion

Tian

Narasimhan

2011

Int J Comput Vis

View full text Add to dashboard Cite

show abstract

“…While it can be computationally expensive, [50] showed that under some conditions, it can be effectively formulated. Since then it has been extended by several authors and applied to 3D tracking [19,65,66].…”

Section: Template Matchingmentioning

confidence: 99%

“…The approach presented in [66] relies on a reinterpretation of Equation (4.13) that yields a faster implementation than the Jacobian formulation discussed above. It treats the equation as an approximation by hyperplanes.…”

Section: Hyperplane Approximationmentioning

confidence: 99%

“…A matrix δp that maps the δi to the δp can then be estimated in the least-squares sense. The paper [66] experimentally shows that such a matrix gives a more reliable approximation of the relation between image differences and the motion. This can be explained by the fact that the objective function of Equation (4.12) has many local minima, which this approach allows the algorithm to skip.…”

Section: Hyperplane Approximationmentioning

confidence: 99%

See 1 more Smart Citation

Monocular Model-Based 3D Tracking of Rigid Objects: A Survey

Lepetit¹,

Fua²

2005

FNT in Computer Graphics and Vision

471

189

View full text Add to dashboard Cite

Many applications require tracking of complex 3D objects. These include visual servoing of robotic arms on specific target objects, Augmented Reality systems that require real-time registration of the object to be augmented, and head tracking systems that sophisticated interfaces can use. Computer Vision offers solutions that are cheap, practical and non-invasive.This survey reviews the different techniques and approaches that have been developed by industry and research. First, important mathematical tools are introduced: Camera representation, robust estimation and uncertainty estimation. Then a comprehensive study is given of the numerous approaches developed by the Augmented Reality and Robotics communities, beginning with those that are based on point or planar fiducial marks and moving on to those that avoid the need to engineer the environment by relying on natural features such as edges, texture or interest. Recent advances that avoid manual initialization and failures due to fast motion are also presented. The survery concludes with the different possible choices that should be made when implementing a 3D tracking system and a discussion of the future of vision-based 3D tracking.Because it encompasses many computer vision techniques from lowlevel vision to 3D geometry and includes a comprehensive study of the massive literature on the subject, this survey should be the handbook of the student, the researcher, or the engineer who wants to implement a 3D tracking system.

show abstract

“…However, tracking algorithms still suffer from fundamental problems including drifts away from targets [4] (partially due to change of viewpoint), inability to adapt to changes of object appearance, dependence on the first frame for template matching [5], instability to track objects under deformations (e.g. deformed contours), the inefficiency of Monte Carlo simulations for temporal tracking [6], and reliance on gradients by active contours [7], i.e.…”

Section: Introductionmentioning

confidence: 99%

Online Feature Selection Using Mutual Information for Real-Time Multi-view Object Tracking

Leung

Gong

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. It has been shown that features can be selected adaptively for object tracking in changing environments [1]. We propose to use the variance of Mutual Information [2] for online feature selection to acquire reliable features for tracking by making use of the images of the tracked object in previous frames to refine our model so that the refined model after online feature selection becomes more robust. The ability of our method to pick up reliable features in real time is demonstrated with multi-view object tracking. In addition, the projective warping of 2D features is used to track 3D objects in non-frontal views in real time. Transformed 2D features can approximate relatively flat object structures such as the two eyes in a face. In this paper, approximations to the transformed features using weak perspective projection are derived. Since features in non-frontal views are computed on-the-fly by projective transforms under weak perspective projection, our framework requires only frontal-view training samples to track objects in multiple views.

show abstract

Hyperplane approximation for template matching

Cited by 184 publications

References 7 publications

Globally Optimal Estimation of Nonrigid Image Distortion

Globally Optimal Estimation of Nonrigid Image Distortion

Monocular Model-Based 3D Tracking of Rigid Objects: A Survey

Online Feature Selection Using Mutual Information for Real-Time Multi-view Object Tracking

Contact Info

Product

Resources

About