Robust localization of furniture parts by integrating depth and intensity data suitable for range sensors with varying image quality

Abstract

In this paper we present an approach to localize planar furniture parts in 3D range camera data for autonomous robot manipulation, that estimates both their six degree of freedom (DoF) poses and their dimensions. Range cameras are a promising sensor category for mobile robotics. Unfortunately, many of them come with a considerable measurement noise, that leads to difficulties when trying to detect objects or their parts e.g. using canonical methods for range image segmentation. In contrast, our approach is able to overcome these issues by combining concepts of 2D and 3D computer vision as well as integrating intensity and depth data on several levels of abstraction. Therefore it is not restricted to range sensors with high image quality and scales on cameras with lower image quality, too. This concept is generic and has been implemented for elliptical object parts as a proof of concept.

Object Detection Applied to Indoor Environments for Mobile Robot Navigation

“…In our work, a combination of different segmentation techniques that do not involve color information is implemented; in this way, problems related to changes in lighting are eliminated, making our algorithm more general to detect different objects, irrespective of color. Other approaches use 3D information for point cloud segmentation, as the work of [ 13 ]. They present an approach to localize planar furniture parts in 3D range camera data.…”