Robotic Vision: Technologies for Machine Learning and Vision Applications

For researchers and practitioners in computer vision and robotics, García-Rodríguez and Cazorla Quevedo (computer technology and artificial intelligence, U. of Alicante, Spain) bring together computer science, engineering, robotics, and technology researchers from Europe, South America, and the US for 22 chapters on computer vision and its applications. They discuss computer vision basics and applications, including face recognition, uniform sampling of rotations for discrete and continuous learning of 2D shape models, basic segmentation methods of video sequences and their combinations, video security systems, visual detection in a linked multi-component robotic systems, building a multiple object tracking system with occlusion handling in surveillance videos, and self-organizing neural networks; 3D data processing applied robotics, with discussion of registration methods for mobile robots, evaluating disparity estimation algorithms, real-time structure estimation in dynamic scenes using a single camera, and intelligent stereo vision in autonomous robot traversability estimation; social robotics systems, such as for imitating gestures, learning to interact socially with humans, assisted living, and human-robot interaction; vision control; and visual attention.