On Hierarchical Models for Visual Recognition and Learning of Objects, Scenes, and Activities

  • Jens Spehr

Part of the Studies in Systems, Decision and Control book series (SSDC, volume 11)

Table of contents

  1. Front Matter
    Pages 1-14
  2. Jens Spehr
    Pages 1-6
  3. Jens Spehr
    Pages 7-20
  4. Jens Spehr
    Pages 21-65
  5. Jens Spehr
    Pages 67-83
  6. Jens Spehr
    Pages 85-120
  7. Jens Spehr
    Pages 121-133
  8. Jens Spehr
    Pages 135-159
  9. Jens Spehr
    Pages 177-184
  10. Back Matter
    Pages 185-199

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.


Activity Recognition Compositional Hierarchies Human-robot Interaction Intelligent Vehicles Probabilistic Graphical Models Mobile Robots Object Recognition Robot Vision Scene Understanding Similarity Hierarchies

Authors and affiliations

  • Jens Spehr
    • 1
  1. 1.Institut für Robotik und ProzessinformatikTechnische Universität BraunschweigBraunschweigGermany

Bibliographic information

  • DOI
  • Copyright Information Springer International Publishing Switzerland 2015
  • Publisher Name Springer, Cham
  • eBook Packages Engineering
  • Print ISBN 978-3-319-11324-1
  • Online ISBN 978-3-319-11325-8
  • Series Print ISSN 2198-4182
  • Series Online ISSN 2198-4190
  • Buy this book on publisher's site
Industry Sectors
Chemical Manufacturing
IT & Software
Energy, Utilities & Environment
Oil, Gas & Geosciences