Eric Brassart

Colour image segmentation using homogeneity method and data fusion techniques

A novel method of colour image segmentation based on fuzzy homogeneity and data fusion techniques is presented. The general idea of mass function estimation in the Dempster-Shafer evidence theory of the histogram is extended to the homogeneity domain. The fuzzy homogeneity vector is used to determine the fuzzy region in each primitive colour, whereas, the evidence theory is employed to merge different data sources in order to increase the quality of the information and to obtain an optimal segmented image. Segmentation results from the proposed method are validated and the classification accuracy for the test data available is evaluated, and then a comparative study versus existing techniques is presented. The experimental results demonstrate the superiority of introducing the fuzzy homogeneity method in evidence theory for image segmentation.

Color image segmentation using automatic thresholding and the fuzzy C-means techniques

In this paper, a color image segmentation approach based on automatic histogram thresholding and the fuzzy C-means (FCM) techniques is presented. The originality of this work remains in using thresholding and clustering techniques together for color image segmentation. The histogram considers the occurrence of the gray levels among pixels. In a first stage, the thresholding histogram is used for finding all major homogenous areas. In order to reduce the computational burden required by the fuzzy C-means, the coarse-fine concept methodology is used. The thresholding technique is used for the coarsely segmentation. After the coarse step, and in order to refine further the segmentation of the assigned pixels which remain unclassified, the fuzzy C-means technique is then applied. The experimental results show that the proposed approach can find homogeneous areas effectively, and can solve the problem of discriminating shading in color images to some extent.

Localization using infrared beacons

In this paper, we deal with a localization system allowing one to determine the position and orientation of a mobile robot. This system uses active beacons distributed at the ceiling of the navigation area. These beacons can transmit a coded infrared signal which allows the robots to identify the sender. A CCD camera associated to an infrared receiver allows one to compute the position with a triangulation method which needs reduced processing time. Calibration and correcting distortion stages are performed to improve accuracy in the determination of the position. Dynamic localisation is established for most actual mobile robots used in indoor areas.

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.

A communication strategy for cooperative robots

In this paper, we present a new language of communication between cooperative mobile robots. Generally, in order to interact they must exchange various information. In mobile robotics, communication can generally only be performed using HF channel. Originally, our language and protocol are designed to carry out safe communication between several ICAR agents (intelligent cooperative autonomous robots), but they can be used to perform another type of communication. We consider mobile robots which must be able to achieve some tasks given by another one, or a supervisor. We are developing a dynamically extendable (i.e. while robots are performing their missions) language which supports nine conversation types and works with twenty six message types. Because of communications nature (radio link), we use macro messages to reduce network congestion.

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.

Color image segmentation based on Dempster-Shafer evidence theory

In this paper, a color image segmentation approach based on Dempster-Shafer evidence theory is presented. The basic technique consists in combining information coming from three independent information sources for the same image. These sources correspond to the three component images R (red), G (green) and B (blue). The Dempster-Shafer theory of evidence is applied in order to fuse the information from these three sources. This method shows the spectacular ability of the evidence theory to handling uncertain, imprecise and incomplete information. The Results on cell images are presented in order to demonstrate the effectiveness of the proposed method.

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.

Estimation of the mass function in the Dempster-Shafer’s evidence theory using automatic thresholding for color image segmentation

In this paper we propose a color image segmentation method based on Demspter-Shaferpsilas theory. The salient aspects of the proposed method are at two levels. Firstly, the mass distributions of the Dempster-Shafer theory are directly derived from the image histogram. Secondly, the fusion of information coming from three different sources for the same image. A new strategy based on an automatic histogram thresholding is proposed to define the mass distributions in the combined framework. The proposed algorithm has been applied to the biomedical images.

A New Method for the Estimation of Mass Functions in the Dempster–Shafer’s Evidence Theory: Application to Colour Image Segmentation

In this paper, the problem of colour image segmentation is addressed using the Dempster–Shafer (DS) theory. Examples are provided showing that this theory is able to take into account a large variety of special situations that occur and which are not well solved using classical approaches. Modelling both uncertainty and imprecision, and computing the conflict between images and introducing a priori information are the main features of this theory. Consequently, the performance of such a segmentation scheme is largely conditioned by the appropriate estimation of mass functions in the DS evidence theory. In this paper, a new method of automatically determining the mass function for colour-image segmentation problems is presented. The mass function of each pixel is determined by applying possibilistic c-means (PCM) clustering to the grey levels of the three primitive colours. A reliability criterion, associated with each pixel and the mass functions of its neighbouring pixels, is used into a fuzzy based reasoning system in order to decide on the appropriate segmentation. Experimental segmentation results on medical and textured colour images highlight the effectiveness of the proposed method.