No abstract

This paper describes methods that use thermal imaging techniques for identifying different types of materials in outdoor scenes. First, we analyze how computer vision techniques applied to thermal images allow discriminating materials such as rock and sand. Second, we present the model that we developed to calculate the temperature of materials. By applying this model, we show that it is possible to determine aphysical characteristic of the material. thermal inertia. Third, as an application. we examine how an autonomous robot can use these techniques to explore other planets. In particuIar, we show how a legged robot CM use thermal inertia and so select where to place its foot next or which material to sample. I .

We are designing a complete autonomous legged robot to perfom planetary exploration without human supervision. This robot must traverse unknown and geographically diverse areas in order a collect samples of materials. This paper describes how a geometric terrain representation from range imagery can be used to identify footfall positions. First, we present previous research aimed to determine footfall positions. Second, we describe several methods for determining the positions for which the shape of the terrain is nearest to the shape of the foot. Third, we evaluate and compare the efficiency of these methods as functions of some parameters such as particularities of the shape of the terrain. Fourth, we introduce other methods that use thermal imaging in order to differentiate materials.

This paper describes how fusion between thermal and range imaging allows us to discriminate different types of materials in outdoor scenes. First, we analyze how pure ViSiOfl segmentation algorithms applied to thermal images allow discriminating materials such as rock and sand. Second, we show how combining thermal and range information allows us to better discriminate rocks from sand. Third, as an application, we examine how an autonomous legged robot can use these techniques to explore other planets.

No abstract