No abstract

Abstract-High resolution depth-maps, obtained by upsampling sparse range data from a 3D-LIDAR, find applications in many fields ranging from sensory perception to semantic segmentation and object detection. Upsampling is often based on combining data from a monocular camera to compensate the lowresolution of a LIDAR. This paper, on the other hand, introduces a novel framework to obtain dense depth-map solely from a single LIDAR point cloud; which is a research direction that has been barely explored. The formulation behind the proposed depth-mapping process relies on local spatial interpolation, using sliding-window (mask) technique, and on the Bilateral Filter (BF) where the variable of interest, the distance from the sensor, is considered in the interpolation problem. In particular, the BF is conveniently modified to perform depth-map upsampling such that the edges (foreground-background discontinuities) are better preserved by means of a proposed method which influences the range-based weighting term. Other methods for spatial upsampling are discussed, evaluated and compared in terms of different error measures. This paper also researches the role of the mask's size in the performance of the implemented methods. Quantitative and qualitative results from experiments on the KITTI Database, using LIDAR point clouds only, show very satisfactory performance of the approach introduced in this work.

No abstract

This paper describes the ISRobotCar, an experimental autonomous electric vehicle that integrates Robot Operating System (ROS) and several sensors such as IBEO laserscanner, Inertial Measurement Unit (IMU), RTK-GPS, vision cameras, and magnet detectors for magnetic guidance. The development of a power steering controller and of a fuzzy path-following controller are particularly addressed. Finally simulations and experimental results of autonomous pathfollowing control are presented.

No abstract

We consider the problem of constructing a Euclidean Steiner tree in a setting where the plane has been divided into polygonal regions, each with an associated weight. Given a set of points (terminals), the task is to construct a shortest interconnection of the points, where the cost of a line segment in a region is the Euclidean distance multiplied by the weight of the region. The problem is a natural generalization of the obstacle-avoiding Euclidean Steiner tree problem, and has obvious applications in network design. We propose an efficient heuristic strategy for the problem, and evaluate its performance on both randomly generated and near-realistic problem instances. The minimum cost Euclidean Steiner tree can be seen as an optical backbone network (a Spine) avoiding disaster prone areas, here represented as higher cost regions.

No abstract

No abstract