Overview
- Provides important basic concepts, efficient methods as well as practical "how-to" examples for the use of hierarchical graphical models
- Discusses the importance and the relationship between sharing and similarity of objects and object parts for efficient recognition and learning approaches
- Comprehensive survey of related work divided in categories such as part-based, compositional or biologically inspired models
- Includes a brief review of probabilistic graphical models
Part of the book series: Studies in Systems, Decision and Control (SSDC, volume 11)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
Table of contents (9 chapters)
Keywords
About this book
In many computer vision applications, objects have to be learned and recognized in images or image sequences. This book presents new probabilistic hierarchical models that allow an efficient representation of multiple objects of different categories, scales, rotations, and views. The idea is to exploit similarities between objects and object parts in order to share calculations and avoid redundant information. Furthermore inference approaches for fast and robust detection are presented. These new approaches combine the idea of compositional and similarity hierarchies and overcome limitations of previous methods. Besides classical object recognition the book shows the use for detection of human poses in a project for gait analysis. The use of activity detection is presented for the design of environments for ageing, to identify activities and behavior patterns in smart homes. In a presented project for parking spot detection using an intelligent vehicle, the proposed approaches are used to hierarchically model the environment of the vehicle for an efficient and robust interpretation of the scene in real-time.
Authors and Affiliations
Bibliographic Information
Book Title: On Hierarchical Models for Visual Recognition and Learning of Objects, Scenes, and Activities
Authors: Jens Spehr
Series Title: Studies in Systems, Decision and Control
DOI: https://doi.org/10.1007/978-3-319-11325-8
Publisher: Springer Cham
eBook Packages: Engineering, Engineering (R0)
Copyright Information: Springer International Publishing Switzerland 2015
Hardcover ISBN: 978-3-319-11324-1Published: 03 December 2014
Softcover ISBN: 978-3-319-35862-8Published: 01 October 2016
eBook ISBN: 978-3-319-11325-8Published: 13 November 2014
Series ISSN: 2198-4182
Series E-ISSN: 2198-4190
Edition Number: 1
Number of Pages: XV, 199
Number of Illustrations: 92 b/w illustrations, 15 illustrations in colour
Topics: Robotics and Automation, Computational Intelligence, Image Processing and Computer Vision, Pattern Recognition