CHAPTER 7
Depth Imaging and Point Clouds
CONTENTS
INTRODUCTION
Ultimately, a robot needs to understand 3-D information from its sensors. This is essential both for computing navigability (e.g. cliffs, ditches, doors, barriers) and manipulation (e.g. how to approach and grasp an object of interest). Some depth information can be inferred from 2-D cameras if a priori assumptions can be invoked. Preferably, sensors would provide unambiguous 3-D data. There are multiple means in common use for 3-D data acquisition. Three of these are discussed in this chapter: tilting LIDAR, stereo vision, and depth cameras. depth imaging
7.1 Depth from scanning LIDAR
Get A Systematic Approach to Learning Robot Programming with ROS now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
