Yohan D. Fougerolle

Central catadioptric image processing with geodesic metric

Because of the distortions produced by the insertion of a mirror, catadioptric images cannot be processed similarly to classical perspective images. Now, although the equivalence between such images and spherical images is well known, the use of spherical harmonic analysis often leads to image processing methods which are more difficult to implement. In this paper, we propose to define catadioptric image processing from the geodesic metric on the unitary sphere. We show that this definition allows to adapt very simply classical image processing methods. We focus more particularly on image gradient estimation, interest point detection, and matching. More generally, the proposed approach extends traditional image processing techniques based on Euclidean metric to central catadioptric images. We show in this paper the efficiency of the approach through different experimental results and quantitative evaluations.

An efficient method for fully automatic 3D digitization of unknown objects

Our goal is to develop a complete and automatic scanning strategy with minimum prior information about the object shape. We aim to establish a methodology for the automation of the 3D digitization process. The paper presents a novel approach to determine the Next Best View (NBV) for an efficient reconstruction of highly accurate 3D models. Our method is based on the classification of the acquired surfaces into Well Visible and Barely Visible combined with a best view selection algorithm based on mean shift, which avoids unreachable positions. Our approach is applicable to all kinds of range sensors. To prove the efficiency and the robustness of our method, test objects are first scanned manually by experts in 3D digitization from the VECTEO company. The comparison of results between manual and automatic scanning shows that our method is very efficient and faster than trained experts. The 3D models of the different objects are obtained with a strongly reduced number of acquisitions while moving efficiently the ranging device. The obtained results prove the effectiveness and the versatility of our 3D reconstruction approach for industrial applications.

Universal natural shapes: From unifying shape description to simple methods for shape analysis and boundary value problems

Gielis curves and surfaces can describe a wide range of natural shapes and they have been used in various studies in biology and physics as descriptive tool. This has stimulated the generalization of widely used computational methods. Here we show that proper normalization of the Levenberg-Marquardt algorithm allows for efficient and robust reconstruction of Gielis curves, including self-intersecting and asymmetric curves, without increasing the overall complexity of the algorithm. Then, we show how complex curves of k-type can be constructed and how solutions to the Dirichlet problem for the Laplace equation on these complex domains can be derived using a semi-Fourier method. In all three methods, descriptive and computational power and efficiency is obtained in a surprisingly simple way.

Genetic Algorithms for Gielis Surface Recovery from 3D Data Sets

In this paper, we apply genetic algorithms to reconstruct Gielis surfaces from 3D data sets. The Levenberg-Marquardt method has been used as a standard for superquadrics recovery and has recently been extended to Gielis surfaces. Unfortunately, the non homogeneity of the Gielis surface parameters requires additional heuristic to determine discrete parameters such as the number of symmetries. Genetic algorithms overcome this issue and provide a more general framework for Gielis surface reconstruction.

Supershape Recovery from 3D Data Sets

In this paper, we apply supershapes and R-functions to surface recovery from 3D data sets. Individual supershapes are separately recovered from a segmented mesh. R-functions are used to perform Boolean operations between the reconstructed parts to obtain a single implicit equation of the reconstructed object that is used to define a global error reconstruction function. We present surface recovery results ranging from single synthetic data to real complex objects involving the composition of several supershapes and holes.

SAFER Vehicle Inspection: A Multimodal Robotic Sensing Platform

The current threats to U.S. security both military and civilian have led to an increased interest in the development of technologies to safeguard national facilities such as military bases, federal buildings, nuclear power plants, and national laboratories. As a result, the Imaging, Robotics, and Intelligent Systems (IRIS) Laboratory at The University of Tennessee (UT) has established a research consortium, known as SAFER (Security Automation and Future Electromotive Robotics), to develop, test, and deploy sensing and imaging systems for unmanned ground vehicles (UGV). The targeted missions for these UGV systems include -- but are not limited to --under vehicle threat assessment, stand-off check-point inspections, scout surveillance, intruder detection, obstacle-breach situations, and render-safe scenarios. This paper presents a general overview of the SAFER project. Beyond this general overview, we further focus on a specific problem where we collect 3D range scans of under vehicle carriages. These scans require appropriate segmentation and representation algorithms to facilitate the vehicle inspection process. We discuss the theory for these algorithms and present results from applying them to actual vehicle scans.

Fully automatic 3D digitization of unknown objects using progressive data bounding box

The goal of this work is to develop a complete and automatic scanning system with minimum prior information. We aim to establish a methodology for the automation of the 3D digitization process. The paper presents a method based on the evolution of the Bounding Box of the object during the acquisition. The registration of the data is improved through the modeling of the positioning system. The obtained models are analyzed and inspected in order to evaluate the robustness of our method. Tests with real objects have been performed and results of digitization are provided.

Radial Supershapes for Solid Modeling

In the previous work, an efficient method has been proposed to represent solid objects as multiple combinations of globally deformed supershapes. In this paper, this framework is applied with a new supershape implicit function that is based on the notion of radial distance and results are presented on realistic models composed of hundreds of hierarchically globally deformed supershapes. An implicit equation with guaranteed differential properties is obtained by simple combinations of the primitives’ implicit representations using R-function theory. The surface corresponding to the zero-set of the implicit equation is efficiently and directly polygonized using the primitives’ parametric forms. Moreover, hierarchical global deformations are considered to increase the range of shapes that can be modeled. The potential of the approach is illustrated by representing complex models composed of several hundreds of primitives inspired from CAD models of mechanical parts.

A robust evolutionary algorithm for the recovery of rational Gielis curves

Gielis curves (GC) can represent a wide range of shapes and patterns ranging from star shapes to symmetric and asymmetric polygons, and even self intersecting curves. Such patterns appear in natural objects or phenomena, such as flowers, crystals, pollen structures, animals, or even wave propagation. Gielis curves and surfaces are an extension of Lame curves and surfaces (superquadrics) which have benefited in the last two decades of extensive researches to retrieve their parameters from various data types, such as range images, 2D and 3D point clouds, etc. Unfortunately, the most efficient techniques for superquadrics recovery, based on deterministic methods, cannot directly be adapted to Gielis curves. Indeed, the different nature of their parameters forbids the use of a unified gradient descent approach, which requires initial pre-processings, such as the symmetry detection, and a reliable pose and scale estimation. Furthermore, even the most recent algorithms in the literature remain extremely sensitive to initialization and often fall into local minima in the presence of large missing data. We present a simple evolutionary algorithm which overcomes most of these issues and unifies all of the required operations into a single though efficient approach. The key ideas in this paper are the replacement of the potential fields used for the cost function (closed form) by the shortest Euclidean distance (SED, iterative approach), the construction of cost functions which minimize the shortest distance as well as the curve length using R-functions, and slight modifications of the evolutionary operators. We show that the proposed cost function based on SED and R-function offers the best compromise in terms of accuracy, robustness to noise, and missing data.

Static-Map and Dynamic Object Reconstruction in Outdoor Scenes Using 3-D Motion Segmentation

This letter aims to build the static-map of a dynamic scene using a mobile robot equipped with 3-D sensors. The sought static-map consists of only the static scene parts, which has a vital role in scene understanding and landmark based navigation. Building static-map requires the categorization of moving and static objects. In this work, we propose a Sparse subspace clustering-based motion segmentation method that categories the static scene parts and the multiple moving objects using their 3D motion trajectories. Our motion segmentation method uses the raw trajectory data, allowing the objects to move in direct 3-D space, without any projection model assumption or whatsoever. We also propose a complete pipeline for static-map building, which estimates the interframe motion parameters by exploiting the minimal 3-point random sample consensus algorithm on the feature correspondences only from the static scene parts. The proposed method has been especially designed and tested for large scene in real outdoor environments. On one hand, our 3-D motion segmentation approach outperforms its 2-D-based counterparts, for extensive experiments on KITTI dataset. On the other hand, separately reconstructed static-maps and moving objects for various dynamic scenes are very satisfactory.