Add to Watchlist

Master Team Project - Robot Driven Library Maintenance

391 views

Citation of segment
Embed Code
Granting licences Cite video
Annotations
Transcript
Extraction of petroleum
Computer animation
Extraction of petroleum
Computer animation
Singing
Extraction of petroleum
Computer animation
Engine
Computer animation
Tin can
Mat
Typesetting
Fur clothing
Reamer
Binoculars
Spaceflight
Game
Rep (fabric)
Gemstone
Computer animation
Hochseeschlepper
Lace
Finger protocol
Caliber
Mint-made errors
Book design
Gate valve
Photographic plate

Metadata

Formal Metadata

Title Master Team Project - Robot Driven Library Maintenance
Author Al Assad, Marouane
Alkhaddour, Rima
Baumert, Erik
Çeşitli, Merve
Gül, Rusen
Lemmens, Maximilian
Zhang, Jie
Zou, Wanlu
Contributors Chair of Software Engineering, University of Mannheim
License CC Attribution 3.0 Germany:
You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor.
DOI 10.5446/21360
Publisher Library of the University of Mannheim
Release Date 2016
Language Silent film

Content Metadata

Subject Area Engineering
Abstract Many librarian tasks require physical presence in the library and are time-consuming and tedious. The SWT Master Team Project "Robot Driven Library Maintenance" was initiated to automate some of these obligations, in order to make more time for more important, value-adding activities. This report demonstrates in detail the four project phases pursued with the goal develop a fully integrated system for the Mannheim University Library which is able to autonomously support the librarians in inventorying books, searching for books, and checking their status. The system comprises a Turtlebot robot which autonomously goes around the desired book shelves, takes pictures of one shelf-level and transfers them to a server. There, using OpenCV and Tesseract, the stickers on the individual books are recognised and the sticker texts extracted. A report engine matches the recognised books with the target condition of the library and saves its report to a database. The reports are made available through a web frontend both via download and as a HTML5 page. Despite the fact that no fully functional system could be built, an impressive proof of concept under realistic conditions could be achieved, and can be further improved to a full-scale system.
Keywords Bibliothek
Inventur
Bildverarbeitung
Automatische Texterkennung (OCR)
Navigation im Raum
Autonomer Roboter
Software-Entwicklung
Loading...
Feedback

Timings

  339 ms - page object

Version

AV-Portal 3.7.0 (943df4b4639bec127ddc6b93adb0c7d8d995f77c)