Advanced Topics in Computer Vision

ISBN-13: 9781447155195 / Angielski / Twarda / 2013 / 433 str.

Giovanni Maria Farinella; Sebastiano Battiato; Roberto Cipolla

Opis

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. This unique text/reference presents a broad selection of cutting-edge research, covering both theoretical and practical aspects of the three main areas in computer vision: reconstruction, registration, and recognition. The book provides an in-depth overview of challenging areas, in addition to descriptions of novel algorithms that exploit machine learning and pattern recognition techniques to infer the semantic content of images and videos. Topics and features: investigates visual features, trajectory features, and stereo matching; reviews the main challenges of semi-supervised object recognition, and a novel method for human action categorization; presents a framework for the visual localization of MAVs, and for the use of moment constraints in convex shape optimization; examines solutions to the co-recognition problem, and distance-based classifiers for large-scale image classification; describes how the four-color theorem can be used in early computer vision for solving MRF problems where an energy is to be minimized; introduces a Bayesian generative model for understanding indoor environments, and a boosting approach for generalizing the k-NN rule; discusses the issue of scene-specific object detection, and an approach for making temporal super resolution video from a single input image sequence.This must-read collection will be of great value to advanced undergraduate and graduate students of computer vision, pattern recognition and machine learning. Researchers and practitioners will also find the book useful for understanding and reviewing current approaches in computer vision.

Recenzje

From the book reviews:

"The goal of this book is to provide an overview of recent works in computer vision. ... The book is intended more for engineers and researchers who will use it as a relevant source of knowledge in the computer vision field, and benefit from the presence of recent and representative methods that are among the best existing solutions to solve the problems reviewed in the book." (Sebastien Lefevre, Computing Reviews, June, 2014)

Spis treści

Visual Features: From Early Concepts to Modern Computer Vision
Martin Weinmann

Where Next in Object Recognition and How Much Supervision Do We Need?
Sandra Ebert and Bernt Schiele

Recognizing Human Actions by Using Effective Codebooks and Tracking
Lamberto Ballan, Lorenzo Seidenari, Giuseppe Serra, Marco Bertini and Alberto Del Bimbo

Evaluating and Extending Trajectory Features for Activity Recognition
Ross Messing, Atousa Torabi, Aaron Courville and Chris Pal

Co-Recognition of Images and Videos: Unsupervised Matching of Identical Object Patterns and its Applications
Minsu Cho, Young Min Shin and Kyoung Mu Lee

Stereo Matching: State-of-the-Art and Research Challenges
Michael Bleyer and Christian Breiteneder

Visual Localization for Micro Aerial Vehicles in Urban Outdoor Environments
Andreas Wendel and Horst Bischof

Moment Constraints in Convex Optimization for Segmentation and Tracking
Maria Klodt, Frank Steinbrücker and Daniel Cremers

Large Scale Metric Learning for Distance-Based Image Classification on Open Ended Data Sets
Thomas Mensink, Jakob Verbeek, Florent Perronnin and Gabriela Csurka

Top-Down Bayesian Inference of Indoor Scenes
Luca Del Pero and Kobus Barnard

Efficient Loopy Belief Propagation Using the Four Color Theorem
Radu Timofte and Luc Van Gool

Boosting k-Nearest Neighbors Classification
Paolo Piro, Richard Nock, Wafa Bel Haj Ali, Frank Nielsen and Michel Barlaud

Learning Object Detectors in Stationary Environments
Peter M. Roth, Sabine Sternig and Horst Bischof

Video Temporal Super-Resolution Based on Self-Similarity
Mihoko Shimano, Takahiro Okabe, Imari Sato and Yoichi Sato

O autorze

Dr. Giovanni Maria Farinella is Adjunct Professor of Computer Science at the University of Catania, Italy, and Contract Professor of Computer Vision at the School of Arts of Catania, Italy. Dr. Sebastiano Battiato is Associate Professor at the University of Catania, Italy. Dr. Roberto Cipolla is Professor of Information Engineeringat the University of Cambridge, UK.