Cyril Drocourt

Mobile robot localization based on an omnidirectional stereoscopic vision perception system

Presents a system of absolute localization based on the stereoscopic omnidirectional vision. To do it we use an original perception system which allows our omnidirectional vision sensor SYCLOP to move along a rail. The first part of our study deals with the problem of building the sensorial model with the help of the two stereoscopic omnidirectional images. To solve this problem we propose an approach based on the fusion of several criteria which will be made according to Dempster-Shafer rules. The second part is devoted to exploiting this sensorial model to localize the robot thanks to matching the sensorial primitives with the environment map. We analyze the performance of our global absolute localization system on several robot elementary moves, in different environments.

Calibration of the omnidirectional vision sensor: SYCLOP

We present a method to calibrate the omnidirectional sensor used in our laboratory, named SYCLOP (conic system for localization and perception). This system, which is able to capture a panoramic image of a 2/spl pi/ radian field, consists of a CCD camera and a vertically oriented conic shaped reflector. In order to have a better precision than that obtained in classical applications using this kind of sensors, we consider the importance of calibration for the whole sensor. After having briefly recalled the theoretical framework used in hard calibration, we design the different transformations made between world object, cone reflector and pictures, as well as the different types of relationship between the world, the cone, the camera and the image coordinates. Finally, we present results obtained with the SYCLOP simulator and an experiment.

Environment exploration using an active vision sensor

An omnidirectional range sensor is reported. This active vision sensor combines a CCD camera and a laser diode. We use two methods to obtain the depth of the scene: a calibration method and a least square method. We describe the prototype we made. Experimental results are presented. A comparative test shows that this sensor seems to be as accurate as a laser telemeter but less sensitive to nonalignment. Its results are better than an ultrasonic sensor. Finally, we compare three segmentation algorithms and their results on the set of points given by the sensor.

Incremental construction of the robot's environmental map using interval analysis

This paper deals with an original simultaneous localisation and map building paradigm (SLAM) based on the one hand on the use of an omnidirectional stereoscopic vision system and on the other hand on an interval analysis formalism for the state estimation. The first part of our study is linked to the problem of building the sensorial model. The second part is devoted to exploiting this sensorial model to localise the robot in the sense of interval analysis. The third part introduces the problem of map updating and deals with the matching problem of the stereo sensorial model with an environment map, (integrating all the previous primitive observations). The SLAM algorithm was tested on several large and structured environments and some experimental results will be presented.

Self localization: a new uncertainty propagation architecture

Abstract In this article, a dynamic localization method based on multi-target tracking is presented. The originality of this method is its capability to manage and propagate uncertainties during the localization process. This multi-level uncertainty propagation stage is based on the use of the Dempster–Shafer theory. The perception system we use is composed of an omnidirectional vision system and a panoramic range finder. It enables us to treat complementary and redundant data and thus to construct a robust sensorial model which integrates an important number of significant primitives. Based on this model, we treat the problem of maintaining a matching and propagating uncertainties on each matched primitive in order to obtain a global uncertainty about the robot configuration.

Simultaneous localization and map construction method using omnidirectional stereoscopic information

This paper deals with the localization and map building paradigm in an unknown indoor environment. We propose an exploration method based on the use of the sensorial data provided by an omnidirectional stereoscopic vision system. First, we link the problem of sensorial model construction with two omnidirectional images. We propose an approach based on the fusion of several criteria, which is realized according to Dempster-Shafer rules. We then deal with the matching problem of the stereo sensorial model with an environment map integrating all the previous primitive observations. We propose two matching approaches based on different selection criteria: the Hausdorff distance and the cumulated Cartesian distance. We also present our incremental map building paradigm based on the hypothesis of a non a priori knowledge. Finally, we deal with the problem of allowing a robot to localize itself and to construct concurrently a representation of its environment.

An absolute localization method using a synthetic panoramic image base

We deal with an absolute mobile robot self-localization algorithm in an artificial indoor environment. Until now, localization methods based on conical omnidirectional vision sensors uniquely used radial segments from vertical environment landmarks projection. The main motivation of this work is to show that primitives other than radial straight lines are usable with a conical vision sensor. In other words, the goal is to demonstrate that the SYCLOP sensor can be used as a vision sensor rather than a goniometric one. After a brief outline of SYCLOP geometry and the calibration process, we show how the calibration allows us to know the omnidirectional image formation process to compute a synthetic image base. Then, we present the localization method. Finally, some experimental results obtained with real noisy omnidirectional images acquired in an artificial indoor environment are shown.

Multisensor cooperation of assistance to driving

We will present in this article the principles of data-processing put into operation within the framework of a research project on the improvement of automobile safety. This project is based on the simultaneous use of two systems of exteroceptive perception: a system of omnidirectional vision with spherical reflector and a telemetric laser. We limit our study to the identification of objects discovered both in panoramic images and in clusters of points stemming from telemetric measures, and this obtained in outside motorway-type environment. After reiterating the mechanisms of creation of the omnidirectional images and clusters of points, we shall detail the various processes which we set up. Finally, we shall dedicate the last part to the experimental results.

Automatic detection of chemotaxis cells in angiogenesis process

A research sector mattering in the medical environment, concerns the study of the neovascularization mechanisms from pre-existing capillary vessels: Angiogenesis. These researches are very important because they correspond to many physiological but also pathological processes: in particular the growth of tumors and the development of the metastases. In this paper we are interested in the particular case of chemotaxis in the field of the angiogenesis. Indeed studies show that according to molecules applied to tumors, the capillary and other vessels develop less quickly, and can be stopped. It allows to reduce the supply to blood nutriments of the tumor and eventually to provoke its degeneration. The study proposed in this paper shows a first application on this subject with a study on in vitro cultures of umbilical cells. During a voluntary incision in a culture of blood cells, and the injection of specific molecules on this wound, we determine the healing speed. The longer the healing time is, the more effective the molecule is. The image analysis that we propose here concerns the detection of blood cells in plate and the detection of the realized incision. The created software of images treatment and the reference images are available on the following site: /www.rteam.iut-amiens.fr/angioscin/.