Springer Tracts in Advanced Robotics

Indoor Scene Recognition by 3-D Object Search

For Robot Programming by Demonstration

Autoren: Meißner, Pascal

Vorschau
  • Focuses on enabling mobile robots to recognize scenes in distributed and cluttered indoor environments
  • Connects two research problems (scene recognition and 3-D object search), which are usually investigated separately in different research fields
  • Presents numerous complex experiments on a real-world robot
Weitere Vorteile

Dieses Buch kaufen

eBook 85,59 €
Preis für Deutschland (Brutto)
  • ISBN 978-3-030-31852-9
  • Versehen mit digitalem Wasserzeichen, DRM-frei
  • Erhältliche Formate: PDF, EPUB
  • eBooks sind auf allen Endgeräten nutzbar
  • Sofortiger eBook Download nach Kauf
Hardcover 149,79 €
Preis für Deutschland (Brutto)
Softcover 106,99 €
Preis für Deutschland (Brutto)
Über dieses Buch

This book focuses on enabling mobile robots to recognize scenes in indoor environments, in order to allow them to determine which actions are appropriate at which points in time. In concrete terms, future robots will have to solve the classification problem represented by scene recognition sufficiently well for them to act independently in human-centered environments. To achieve accurate yet versatile indoor scene recognition, the book presents a hierarchical data structure for scenes – the Implicit Shape Model trees. Further, it also provides training and recognition algorithms for these trees. In general, entire indoor scenes cannot be perceived from a single point of view. To address this problem the authors introduce Active Scene Recognition (ASR), a concept that embeds canonical scene recognition in a decision-making system that selects camera views for a mobile robot to drive to so that it can find objects not yet localized. The authors formalize the automatic selection of camera views as a Next-Best-View (NBV) problem to which they contribute an algorithmic solution, which focuses on realistic problem modeling while maintaining its computational efficiency. Lastly, the book introduces a method for predicting the poses of objects to be searched, establishing the otherwise missing link between scene recognition and NBV estimation.

Inhaltsverzeichnis (6 Kapitel)

Inhaltsverzeichnis (6 Kapitel)

Dieses Buch kaufen

eBook 85,59 €
Preis für Deutschland (Brutto)
  • ISBN 978-3-030-31852-9
  • Versehen mit digitalem Wasserzeichen, DRM-frei
  • Erhältliche Formate: PDF, EPUB
  • eBooks sind auf allen Endgeräten nutzbar
  • Sofortiger eBook Download nach Kauf
Hardcover 149,79 €
Preis für Deutschland (Brutto)
Softcover 106,99 €
Preis für Deutschland (Brutto)
Loading...

Bibliografische Information

Bibliographic Information
Buchtitel
Indoor Scene Recognition by 3-D Object Search
Buchuntertitel
For Robot Programming by Demonstration
Autoren
Titel der Buchreihe
Springer Tracts in Advanced Robotics
Buchreihen Band
135
Copyright
2020
Verlag
Springer International Publishing
Copyright Inhaber
Springer Nature Switzerland AG
eBook ISBN
978-3-030-31852-9
DOI
10.1007/978-3-030-31852-9
Hardcover ISBN
978-3-030-31851-2
Softcover ISBN
978-3-030-31854-3
Buchreihen ISSN
1610-7438
Auflage
1
Seitenzahl
XIX, 262
Anzahl der Bilder
27 schwarz-weiß Abbildungen, 89 Abbildungen in Farbe
Themen