Th eme 3 | I n teraction homme-machine, images, donn ees, connaissances Projet MOVI Rapport de recherche n3338 | Janvier 1998 | 34 pagesAbstract: 3D measurements can berecovered from several views by triangulation. This paper deals with the problem of where to place the cameras in order to obtain a minimal error in the 3D measurements, also called camera network design in photogrammetry. We pose the problem in terms of an optimization design, dividing it into two main components: 1 an analytical part dedicated to the analysis of error propagation from which a criterion is derived, 2 a global optimization process to minimizes this criterion. In this way, the approach consists of an uncertainty analysis applied to the reconstruction process from which a covariance matrix is computed. This matrix represents the uncertainty of the detection from which the criterion is derived. Moreover, the optimization has discontinuities mainly due to the unobservability of points, which leads to a combinatorial optimization process. These aspects are solved using a multicellular genetic algorithm. Experimental results are provided to illustrate the e ectiveness and e ciency of the solution.Keywords: Camera network design, uncertainty analysis, global optimization, covariance matrix, genetic algorithms.R esum e : tsvp De ce côt e-l a, l'approche consiste en une analyse d'incertitude appliqu ee au processus de reconstruction d'o u une matrice de covariance sera calcul ee. Cette matrice repr esente l'incertitude de la detection pour lequel le crit ere est d eriv e. Par ailleurs, l'optimisation a des aspects discontinus essentiellement dû a l'inobservabilit e des points. Ce facteur va nous amener a utiliser un processus d'optimisation combinatoire que nous avons r esolu en utilisant un algorithme g en etique multicellulaire. Des resultats exp erimentaux sont inclus pour illustrer l'e cacit e et la rapidit e de la solution.

No abstract

This work describes how evolutionary computation can be used to synthesize low-level image operators that detect interesting points on digital images. Interest point detection is an essential part of many modern computer vision systems that solve tasks such as object recognition, stereo correspondence, and image indexing, to name but a few. The design of the specialized operators is posed as an optimization/search problem that is solved with genetic programming (GP), a strategy still mostly unexplored by the computer vision community. The proposed approach automatically synthesizes operators that are competitive with state-of-the-art designs, taking into account an operator's geometric stability and the global separability of detected points during fitness evaluation. The GP search space is defined using simple primitive operations that are commonly found in point detectors proposed by the vision community. The experiments described in this paper extend previous results (Trujillo and Olague, 2006a,b) by presenting 15 new operators that were synthesized through the GP-based search. Some of the synthesized operators can be regarded as improved manmade designs because they employ well-known image processing techniques and achieve highly competitive performance. On the other hand, since the GP search also generates what can be considered as unconventional operators for point detection, these results provide a new perspective to feature extraction research.

No abstract

This work presents a novel local image descriptor based on the concept of pointwise signal regularity. Local image regions are extracted using either an interest point or an interest region detector, and discriminative feature vectors are constructed by uniformly sampling the pointwise Hölderian regularity around each region center. Regularity estimation is performed using local image oscillations, the most straightforward method directly derived from the definition of the Hölder exponent. Furthermore, estimating the Hölder exponent in this manner has proven to be superior, in most cases, when compared to wavelet based estimation as was shown in previous work. Our detector shows invariance to illumination change, JPEG compression, image rotation and scale change. Results show that the proposed descriptor is stable with respect to variations in imaging conditions, and reliable performance metrics prove it to be comparable and in some instances better than SIFT, the state-of-the-art in local descriptors.