René Husson

An Optimized Segmentation Method for a 2D Laser-Scanner Applied to Mobile Robot Navigation

Abstract This article presents a system for segmentation the data of a laser scanner on board a mobile robot. Three algorithms were tested in three different environments. They were compared in terms of their robust segmentation for indoor and outdoor environments, good representation of the environment and their handling for the map building. For environment modelling a polygonal representation was chosen. Furthermore, it should have good real-time capability to be able to integrate the information of the laser-scanner into the navigation algorithms of the mobile robot.

Capture of homotopy classes with probabilistic road map

Feasibility tests in virtual reality for nuclear power plant maintenance or dismantling operations are a source of problems for motion planning because finding a way in a cluttered environment is not easy for the bulky loads, mobile devices and robots used in such operations. Standard probabilistic roadmap methods (PRM) have been successfully used to answer such feasibility problems. These methods provide, at the most a single solution but do not provide a complete overview of the possible motions which have to be evaluated in a complete engineering task. We focus here on the open question of building probabilistic roadmaps which can provide an exhaustive list of all the solutions which can not be distorted from one to another while staying collision free. We call such roadmaps homotopy preserving probabilistic roadmap (HPPR). We propose a new algorithm for creating HPPR.

Vehicle detection at night using image processing and pattern recognition

We present a methodology to detect vehicles at night using image processing and pattern recognition. The using of mathematical morphology, the techniques of pattern recognition and the studying of perspective influences are the major innovations of our method. First, we present an initialisation phase that involves a road modelling. Afterwards, we present methodologies to detect vehicles on highways. We also discuss the results and give perspectives and conclusions.<<ETX>>

ECG Data Compression Using Jacobi Polynomials

Data compression is a frequent signal processing operation applied to ECG. We present here a method of ECG data compression utilizing Jacobi polynomials. ECG signals are first divided into blocks that match with cardiac cycles before being decomposed in Jacobi polynomials bases. Gauss quadratures mechanism for numerical integration is used to compute Jacobi transforms coefficients. Coefficients of small values are discarded in the reconstruction stage. For experimental purposes, we chose height families of Jacobi polynomials. Various segmentation approaches were considered. We elaborated an efficient strategy to cancel boundary effects. We obtained interesting results compared with ECG compression by wavelet decomposition methods. Some propositions are suggested to improve the results.

A standard model of the placement problem aimed at resolving a cutting stock problem

The authors propose a wood cutting optimization technique to deal with a class of problems, in which dimensions of objects to be cut are unknown beforehand. The technique is based on a two-level hierarchical structure: a placement algorithm charged on a given plank to optimize the cutting and a process control procedure permitting production of a requested list of pieces in the best way on a limited horizon. The placement algorithm is modeled in order to formalize the control strategy. In particular, a method for connecting a system of discrete events to the more classical theory of continuous sampled systems is proposed. With this model, and under the given hypothesis, an optimal control policy is established.<<ETX>>

Analysis and inspection of road traffic using image processing

A methodology using image processing to detect vehicles on highways is presented in this paper. Vehicle detection is done in two stages. In stage one, the dimensional and morphological study of the analyzed highway is carried out in order to model and calibrate the vision system. In stage two, vehicles are detected owing to the method of matching clear and dark blobs. These are extracted by mathematical morphology techniques and bright headlight images by using pattern recognition techniques. The position of the vehicle allows access to spatial-temporal information which characterize traffic flow and permit automatic traffic control.

Sensor Cooperation and World Perception of the Autonomous Mobile Robot Romane

Abstract This paper presents a map building method of an autonomous mobile robots environment. It is based on an original « focus of attention » cooperation system using a laser rangefinder as the main source of information and a video camera mounted on a pantilt unit to perform close inspection of selected objects in the scene; selection of such objects being performed by analysing data from the laser rangefinder. This cooperation process provides a sufficiently rich description of the robots environment to call for more complex tasks such as localisation.

Road modelling and vehicle detection by using image processing

In this paper, we present methodologies of motion detection using vision system applied to road traffic. The using of mathematical morphology, the studying of perspective influences and signal processing are representing the major innovation of our methodologies. First, we present the state of the art and an initialisation phase which involves road modelling and calibration of the vision system. Secondly, we present methodologies for vehicle detection on highway. After, we present a method to detect then separate tight vehicles. At last, we discuss results and give perspectives and conclusions.<<ETX>>

Map database construction and scene prediction for visual navigation

In this paper an image is used to construct a map database for an autonomous navigation system. In fact, this map image looks like an aerial image taken at a certain altitude h. The level of the pixels belonging to a static object have been set to a value proportional to the object height. The aim of this method is to provide the vision system with what would almost be the 3-D scene appearance at any given point of the map specified by the navigation task. The construction method is fully detailed; moreover, the contribution of this work to the road edge selection algorithm is investigated and compared to the Hough transform based selection. This algorithm constitutes an efficient tool for object localization and identification, and a powerful support to the road edge selection task.

Systeme de vision utilisant le flou optique: application a la recherche automatique de defauts d'aspects

The possibilities of a hybrid image processor, entitled Net Flou, used for the automatic detection of defects are presented. In this paper, the new idea is to optimize the Net-Flou system to detect defects with particular spatial frequency characteristics. An application example in detecting visual defects of mechanical objects (connecting rods) will be illustrated.