Abstract. This paper presents a solution of the appearance-based people reidentification problem in a surveillance system including multiple cameras with different fields of vision. We first utilize different color-based features, combined with several illuminant invariant normalizations in order to characterize the silhouettes in static frames. A graph-based approach which is capable of learning the global structure of the manifold and preserving the properties of the original data in a lower dimensional representation is then introduced to reduce the effective working space and to realize the comparison of the video sequences. The global system was tested on a real data set collected by two cameras installed on board a train. The experimental results show that the combination of color-based features, invariant normalization procedures and the graph-based approach leads to very satisfactory results.

This paper presents the kinematics of a planar multibody vehicle which is aimed at the exploration, data collection, non-destructive testing and general autonomous navigation and operations in confined environments such as pipelines. The robot is made of several identical modules hinged by passive revolute joints. Every module is actuated with four active revolute joints and can be regarded as a parallel

-The ICP (Iterative Closest Point) algorithm remains a very popular method for the registration of 3D data sets, when an initial guess of the relative pose between them is known. The purpose of the work presented in this paper is to improve performance of classical ICP. We address, here, the problem of pair-wise registration of color range images. Many variants of ICP have been proposed for the registration of 3D data sets. However, there are only a few solutions dealing with color range images. In this paper, we have adapted some variants of ICP to take into account color information in the closest point research. Two approaches of color data integration have been evaluated with real 3D/Color data sets.

In this paper, we study the dynamics of an articulated planar mobile robot for confined environment exploration. The mobile vehicle is composed of n identical modules hitched together with passive revolute joints. Each module has the structure of a four-bar parallel mechanism on a mobile platform. The dynamic model is derived using Lagrange formulation. Computer simulations illustrate the model by addressing a path following problem inside a pipe. The dynamic model presented in this paper is the basis for the design of motion control algorithms that encode energy optimization and sensor performance maximization. Introduction and Related LiteratureThis work is part of a project aimed at the development of a three-dimensional autonomous articulated mobile robot for the exploration and nondestructive testing in confined environments that can be hazardous or not accessible to humans. One application targeted by this system is natural gas pipelines inspection. Articulated mobile robots made their appearance in the framework of service robotics [1]. Snake-like mobile robots are often chosen for the class of applications we are interested in because of their great agility and high redundancy, which enable them to operate in environments that might be too challenging for a conventional wheeled robot. For instance, they are conveniently deployed inside pipelines [2], in narrow spaces, and on the rubble of an earthquake or a major fire, and find applications in fields as diverse as rescue operations, military/defense, and confined environment exploration as, for example, inspection of bridges [3], inspection of natural gas pipelines, industrial pipes and sewer pipelines [4][5][6][7][8][9], to name a few. Snake-like robots proposed in the literature are typically locomoted either with passive caster wheels supporting their frames [10][11][12] or with no wheels at all [13][14][15][16].