SIMD extensions have been a feature of choice for processor manufacturers for a couple of decades. Designed to exploit data parallelism in applications at the instruction level and provide significant accelerations, these extensions still require a high level of expertise or the use of potentially fragile compiler support or vendor-specific libraries. In this poster, we present Boost.SIMD a C++ template library that simplifies the exploitation of SIMD hardware within a standard C++ programming model.

Pedestrian recognition in images is a challenging task. Indeed a generic model must be 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 a classical AdaBoost method.

The paper deals with autonomous environment mapping, localisation and navigation using exclusively monocular vision and multiple 2D pattern tracking. The environment map is a mosaic of 2D patterns detected on the ceiling plane and used as natural landmarks. The robot is able to reproduce learned trajectories defined by key images representing the visual memory. The pattern tracker is based on particle filetring. It uses both image contours and gray scale level variations to track efficiently 2D patterns on cluttered background. An original observation model used for filter state updating is presented.

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.

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.

International audience

Recent progress in monocular localization of modelled objects allow to design a robot command based on pose from visual information. The computing time of such algorithms was was once too great for them to be used in real-time closed-loop control, but this is no longer so. The principle of this command is to control the camera location relative to the pose of a target object: this approach is not only straightforward, but moreover it is fairly general in the fact that it does not depend on the visual information which is treated but only of the localization delivered by these treatments. This command has been implemented on a camera-equipped robotic system, a Cartesian robot arm, to track volumic objects.

We describe and compare two approaches to achieve segments matching between two images from a sequence, without any knowledge on the viewed object and/or on the motion of the camera between the different images. The first method uses an Hopfield neural network with several local constraints like correlation and distance between segments of consecutive images. The second algorithm is an iterative optimization of a criterion. We model the primitives displacement between the images by an homographic transform. Then we search, with a Levenberg-Marquardt method, the homography matrix giving the best match between the segments of the two images. The two algorithms are validated and compared on sequences of real images.

Our paper proposes a new model based approach to locate and track an object in a multi-cameras system: this method does not involve triangulation. If the calibration and the mutual geometry of the acquisition systems are known, it is possible to express the whole set of equations pertaining to each monocular system, in an unique reference system. In this way it is possible to show that based model methods are not restricted to monocular vision and that some techniques generally viewed as purely monocular can be readily extended and integrated to a multi-cameras system. We prove by experiments on sequences of real images that this approach leads to results better than the monocular ones in two directions: better accuracy as many different view points are used; better robustness as the system is able to deal gracefully with the loss of some of the captors.>

Presents a method for estimating the radial distortion generated by the lenses of an optical system. This method is based on the properties of a projective invariant: the cross ratio of four collinear points. It provides an iterative correction algorithm which computes images of planar grids. The calculated distortion curve is modeled by a cubic B-spline. Experiments with both synthetic and real data prove the validity of the approach. Furthermore, to show the effect of the radial distortion correction, results of different localization processes applied to corrected and uncorrected images are reported and compared.>

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.

An algorithm for recovering the scaling function of a straight homogeneous generalized cylinder (SHGC) from an image contour is presented. Both location and reference cross section are supposed known. Perspective view assumption and geometric properties of SHGCs are used to derive the method. No additional constraints have been imposed on the object shape. The method has been tested on synthetic image, with promising results.>

A system is presented for modelling solids of revolution from a set of a few monocular images. The reconstruction is obtained by assuming only that the viewed object belongs to this particular class of objects. The knowledge of the camera displacement between each image is not required. The modeling is based on the resolution of the inverse perspective problem for the contour points detected in the different images.>

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.>

The authors proposed the localization of some kinds of generalized cylinders from their brightness image by solving the inverse perspective transform of their contours. Geometrical properties of perspective projection of zero-curvature points of space or planar curves are used for that. The main geometrical properties are exploited in two experiments. These experiments involve straight homogeneous cylinder and objects of revolution with a scaling function having at least one zero-curvature point. Knowing the model of these objects, it is shown that their spatial attitude can be recovered from their perspective image.>

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.>

A method to find the analytical solutions of the inverse perspective problem for the determination of the 3-D object attitude 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 triplet of linear ridges of the object model. The geometrical transformations to apply to the model to bring it into the corresponding location are obtained by the resolution of an eighth-degree equation. The number of admissible solutions can still be reduced, using simple pruning rules. This approach leads to very strong results useful for both location and recognition of 3D objects. Because few admissible hypotheses are retained, the line-matching procedure by prediction-verification is less complex.>

A new and unified approach is proposed for ridge and contour points detection in textures. It involves a 3D-representation of a greylevel image and a description of the surface thus obtained, with local curvature properties. Some theoretical foundations are first recalled and used for the extraction of ridge and contour points from the convex domains of the image surface. Experimental results are given in the case of crystallization images of biological substratums, in which radiance centers are looked for.