Introduction to AI Robotics, Second Edition by Murphy Robin R.;
Author:Murphy, Robin R.;
Language: eng
Format: epub
Tags: Algorithm; Artificial Intelligence; AI; robotics; robots; computer science; sensing; navigation; uncertainty; hierarchical robotics; reactive robotics; hybrid deliberation/reactive robotics; multiagent; path-planning; mobile robots; computer vision; range sensing
Publisher: MIT Press
11.4.3â RGB-D Cameras
RGB-D CAMERA
RGB-D cameras are a combination of a IR light striping system (except instead of stripes of light, random dots are projected) with a regular RGB visible light camera. These are sometimes called RGB+D or just RGBD cameras. RGB-D cameras project IR light read by a camera tuned for the IR frequency of light. The IR dots are invisible to the human eye. Thus a separate RGB camera can be mounted next to the IR camera to perceive the same scene without dots and make it visible to the human eye. The low-cost Microsoft Kinect and ASUS Xtion cameras use essentially the same technology for videogames and were immediately adopted for use by roboticists.
However, as noted in Suarez and Murphy,201 the RGB-D cameras are not sufficient for general robotics for three reasons. First, RGB-D cameras are typically optimized for the videogame market, where the camera is stationary, indoors, and the gamer adjusts the lighting in the room and turns the camera system until it produces consistent results. In mobile robots, the robot may move through regions that have much different lighting conditions than does an indoor recreational room. Bright light and direct sunlight wash out the IR projection. Second, the IR light is an active sensor. Thus objects with reflective surfaces or sharp edges and angular surfaces that create specular reflection cause the IR image to be noisy. Third, RGB-D cameras are tuned for projection and receptivity over specific ranges. In the case of a Kinect, that range is 1.2 m to 3.5 m. If a robot needs to perceive depth closer than 1.2 m or farther than 3.5 m, the Kinect will not be of use.
Download
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.
Algorithms of the Intelligent Web by Haralambos Marmanis;Dmitry Babenko(8309)
Test-Driven Development with Java by Alan Mellor(6773)
Data Augmentation with Python by Duc Haba(6688)
Principles of Data Fabric by Sonia Mezzetta(6435)
Learn Blender Simulations the Right Way by Stephen Pearson(6335)
Microservices with Spring Boot 3 and Spring Cloud by Magnus Larsson(6209)
Hadoop in Practice by Alex Holmes(5965)
Jquery UI in Action : Master the concepts Of Jquery UI: A Step By Step Approach by ANMOL GOYAL(5813)
RPA Solution Architect's Handbook by Sachin Sahgal(5605)
Big Data Analysis with Python by Ivan Marin(5387)
The Infinite Retina by Robert Scoble Irena Cronin(5298)
Life 3.0: Being Human in the Age of Artificial Intelligence by Tegmark Max(5154)
Pretrain Vision and Large Language Models in Python by Emily Webber(4352)
Infrastructure as Code for Beginners by Russ McKendrick(4116)
Functional Programming in JavaScript by Mantyla Dan(4042)
The Age of Surveillance Capitalism by Shoshana Zuboff(3961)
WordPress Plugin Development Cookbook by Yannick Lefebvre(3832)
Embracing Microservices Design by Ovais Mehboob Ahmed Khan Nabil Siddiqui and Timothy Oleson(3632)
Applied Machine Learning for Healthcare and Life Sciences Using AWS by Ujjwal Ratan(3605)
