Jean-Thierry Lapresté

Determination of the attitude of 3D objects from a single perspective view

A method for finding analytical solutions to the problem of determining the attitude of a 3D object in space from a single perspective image is presented. Its principle is based on the interpretation of a triplet of any image lines as the perspective projection of a triplet of linear ridges of the object model, and on the search for the model attitude consistent with these projections. The geometrical transformations to be applied to the model to bring it into the corresponding location are obtained by the resolution of an eight-degree equation in the general case. Using simple logical rules, it is shown on examples related to polyhedra that this approach leads to results useful for both location and recognition of 3D objects because few admissible hypotheses are retained from the interpolation of the three line segments. Line matching by the prediction-verification procedure is thus less complex. >

QUAFF: efficient C++ design for parallel skeletons

We present QUAFF, a new skeleton-based parallel programming library. Its main originality is to rely on C++ template meta-programming techniques to achieve high efficiency. In particular, by performing most of skeleton instantiation and optimization at compile-time, QUAFF can keep the overhead traditionally associated to object-oriented implementations of skeleton-based parallel programming libraries very small. This is not done at the expense of expressivity. This is demonstrated in this paper by several applications, including a full-fledged, realistic real-time vision application.

Inverse perspective transform using zero-curvature contour points: application to the localization of some generalized cylinders from a single view

The localization of some kinds of modeled generalized cylinders from a single brightness perspective image is addressed. It is shown how the zero-curvature points of their contours can be used to solve the inverse perspective problem. Three key theorems about the perspective projection of space curves and of the limbs of a straight homogeneous generalized cylinder whose scaling function has at least one zero-curvature point are discussed. In view of the localization of homogeneous generalized cylinders, an algorithm previously developed by the authors which estimates the pose of a line-triplet is adapted. A new theoretical result about the inverse perspective projection of cones of revolution useful for the localization of objects of revolution is presented. The corresponding algorithms have been implemented, and results of experiments demonstrate the feasibility of the proposed localization methods. >

Modelled Object Pose Estimation and Tracking by Monocular Vision.

This paper presents a new method that permits to solve the problem of determination of a modelled 3D-object spatial attitude from a single perspective image and to compute the covariance matrix associated to the attitude parameters. Its principle is based on the interpretation of at least three segments as the perspective projection of linear ridges of the object model and on the iterative search ( using Kalman filtering) of the model attitude consistent with these projections. The knowledge of the attitude and of the associated covariances enables to use a higher level Kalman filter to track an object along an image sequence. In the tracking process this Kalman filter is used to predict the attitude of the object and the error matrices are used to make robust automatic matches between the image segments and the model ridges. Tracking experiments have been made that proves the validity of this approach. This work has been partially supported by a contract with the European Spatial Agency (ESA) in which society Sagem is the prime contractor.

An efficient method to compute the inverse Jacobian matrix in visual servoing

The work presents a method for estimating the inverse Jacobian matrix of a function, without computing the direct Jacobian matrix. The resulting inverse Jacobian matrix is shown to perform much better in modelling a relation /spl theta/ = f/sup -1/ (x) than the classical Moore-Penrose inverse J/sup +//sub f/. Theoretical insight as well as comparisons in the domain of visual servoing are provided to demonstrate this assertion.

Camera calibration from spheres images

From spheres images we have developed a new method for camera calibration in order to calculate with accuracy its intrinsic parameters. We prove an interesting geometric propriety about ellipses extracted from sphere images. Taking into account the lens geometrical distortion introduced by the optical system and searching a precise points detection for spheres images, permit to obtain satisfactory results.

Real-time tracking with classifiers

Two basic facts motivate this paper: (1) particle filter based trackers have become increasingly powerful in recent years, and (2) object detectors using statistical learning algorithms often work at a near real-time rate. We present the use of classifiers as likelihood observation function of a particle filter. The original resulting method is able to simultaneously recognize and track an object using only a statistical model learnt from a generic database. Our main contribution is the definition of a likelihood function which is produced directly from the outputs of a classifier. This function is an estimation of calibrated probabilities P(class|data). Parameters of the function are estimated to minimize the negative log likelihood of the training data, which is a cross-entropy error function. Since a generic statistical model is used, the tracking does not need any image based model learnt inline. Moreover, the tracking is robust to appearance variation because the statistical learning is trained with many poses, illumination conditions and instances of the object. We have implemented the method for two recent popular classifiers: (1) Support Vector Machines and (2) Adaboost. An experimental evaluation shows that the approach can be used for popular applications like pedestrian or vehicle detection and tracking. Finally, we demonstrate that an efficient implementation provides a real-time system on which only a fraction of CPU time is required to track at frame rate.

A Hessian approach to visual servoing

The paper presents a method for estimating the control matrix in visual servoing using approximation up to the second order of the projection function. The classical approach simply uses the first order terms (inverse of the interaction matrix). The resulting control matrix is shown to perform much better than the classical one. Peculiarly, translation are made almost completely independent of z rotations, allowing better spatial trajectories. Theoretical insight as well as comparisons in the domain of visual servoing are provided to demonstrate this assertion.

Association of AdaBoost and Kernel based machine learning methods for visual pedestrian recognition

We present a real-time solution for pedestrian detection in images. The key point of such method is the definition of a generic model able to describe the huge variability of pedestrians. We propose a learning based approach using a training set composed by positive and negative samples. A simple description of each candidate image provides a huge feature vector from which can be built weak classifiers. We select a subset of relevant weak classifiers using a classic AdaBoost algorithm. The resulting subset is then used as binary vectors in a kernel based machine learning classifier (like SVM, RVM, ...). The major contribution of the paper is the original association of an AdaBoost algorithm to select the relevant weak classifiers, followed by a SVM like classifier for which input data are given by the selected weak classifiers. Kernel based machine learning provides non-linear separator into the weak classifier space while standard AdaBoost gives a linear one. Performances of this method are compared to state of art methods and a real-time application with a monocular camera embedded in a moving vehicle is also presented to match this approach against a real context.

Dense Reconstruction by Zooming

Reconstruction by zooming is not an unachievable task. As it has been previously demonstrated, axial stereovision technics allows to infer 3D information, but involves very small triangulation angles. Accurate calibration, data matching and reconstruction have to be performed to obtain satisfactory modelling results. In this paper, a new approach is proposed to realize dense reconstruction using a static camera equipped with a zoom lens.