Computer vision is the science and technology of making machines that see. It is concerned with the theory, design and implementation of algorithms that can automatically process visual data to recognize objects, track and recover their shape and spatial layout. The International Computer Vision Summer School - ICVSS was established in 2007 to provide both an objective and clear overview and an in-depth analysis of the state-of-the-art research in Computer Vision. The courses are delivered by world renowned experts in the field, from both academia and industry, and cover both theoretical and practical aspects of real Computer Vision problems. The school is organized every year by University of Cambridge (Computer Vision and Robotics Group) and University of Catania (Image Processing Lab). Different topics are covered each year. A summary of the past Computer Vision Summer Schools can be found at: http://www.dmi.unict.it/icvss This edited volume contains a selection of articles covering some of the talks and tutorials held during the first two editions of the school on topics such as Recognition, Registration and Reconstruction. The chapters provide an in-depth overview of these challenging areas with key references to the existing literature. Is human vision any good? -- Jan J. Koenderink Knowing a good feature when you see it : ground truth and methodology to evaluate local features for recognition -- Andrea Vedaldi, Haibin Ling, Stefano Soatto Dynamic graph cuts and their applications in computer vision -- Pushmeet Kohli, Philip H.S. Torr Discriminative graphical models for context-based classification -- Sanjiv Kumar From the subspace methods to the mutual subspace method -- Ken-ichi Maeda What, where and who? Telling the story of an image by activity classification, scene recognition and object categorization -- Li Fei-Fei, Li-Jia Li Semantic texton forests -- Matthew Johnson, Jamie Shotton Multi-view object categorization and pose estimation -- Silvio Savarese, Li Fei-Fei A vision-based remote control -- Björn Stenger, Thomas Woodley, Roberto Cipolla Multi-view multi-object detection and tracking -- Murtaza Taj, Andrea Cavallaro Shape from photographs : a multi-view stereo pipeline -- Carlos Hernández, George Vogiatzis Practical 3D reconstruction based on photometric stereo -- George Vogiatzis, Carlos Hernández. Front Matter....Pages - Is Human Vision Any Good?....Pages 1-25 Knowing a Good Feature When You See It: Ground Truth and Methodology to Evaluate Local Features for Recognition....Pages 27-49 Dynamic Graph Cuts and Their Applications in Computer Vision....Pages 51-108 Discriminative Graphical Models for Context-Based Classification....Pages 109-134 From the Subspace Methods to the Mutual Subspace Method....Pages 135-156 What, Where and Who? Telling the Story of an Image by Activity Classification, Scene Recognition and Object Categorization....Pages 157-171 Semantic Texton Forests....Pages 173-203 Multi-view Object Categorization and Pose Estimation....Pages 205-231 A Vision-Based Remote Control....Pages 233-262 Multi-view Multi-object Detection and Tracking....Pages 263-280 Shape from Photographs: A Multi-view Stereo Pipeline....Pages 281-311 Practical 3D Reconstruction Based on Photometric Stereo....Pages 313-345 Back Matter....Pages - The series Studies in Computational Intelligence (SCI) publishes new developments and advances in the various areas of computational intelligence - quickly and with a high quality. The intent is to cover the theory, applications, and design methods of computational intelligence, as embedded in the fields of engineering, computer science, physics and life science, as well as the methodologies behind them. The series contains monographs, lecture notes and edited volumes in computational intelligence spanning the areas of neural networks, connectionist systems, genetic algorithms, evolutionary computation, artificial intelligence, cellular automata, self-organizing systems, soft computing, fuzzy systems and hybrid intelligent systems. Critical to both contributors and readers are the short publication time and world-wide distribution - this permits a rapid and broad dissemination of research results
