• search hit 2 of 0
Back to Result List

Subobject Detection through Spatial Relationships on Mobile Phones

  • We present a novel image classification technique for detecting multiple objects (called subobjects) in a single image. In addition to image classifiers, we apply spatial relationships among the subobjects to verify and to predict locations of detected and undetected subobjects, respectively. By continuously refining the spatial relationships throughout the detection process, even locations ofWe present a novel image classification technique for detecting multiple objects (called subobjects) in a single image. In addition to image classifiers, we apply spatial relationships among the subobjects to verify and to predict locations of detected and undetected subobjects, respectively. By continuously refining the spatial relationships throughout the detection process, even locations of completely occluded exhibits can be determined. Finally, all detected subobjects are labeled and the user can select the object of interest for retrieving corresponding multimedia information. This approach is applied in the context of PhoneGuide, an adaptive museum guidance system for camera-equipped mobile phones. We show that the recognition of subobjects using spatial relationships is up to 68% faster than related approaches without spatial relationships. Results of a field experiment in a local museum illustrate that unexperienced users reach an average recognition rate for subobjects of 85.6% under realistic conditions.show moreshow less

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Document Type:Article
Author: Benjamin Brombach, Erich Bruns, Oliver BimberORCiDGND
DOI (Cite-Link):https://doi.org/10.25643/bauhaus-universitaet.1353Cite-Link
URN (Cite-Link):https://nbn-resolving.org/urn:nbn:de:gbv:wim2-20081007-14296Cite-Link
Language:English
Date of Publication (online):2008/10/07
Year of first Publication:2008
Release Date:2008/10/07
Contributing Corporation:Stiftung für Technologie, Innovation und Forschung Thüringen (STIFT)
Institutes and partner institutions:Fakultät Medien / Junior-Professur Augmented Reality
Tag:Museumsführer; Neuronales Netz; Räumliche Beziehungen; Subobjekterkennung
Museum Guidance; Neural Networks; Spatial Relationships; Subobject Detection
GND Keyword:Objekterkennung; Smartphone
Dewey Decimal Classification:000 Informatik, Informationswissenschaft, allgemeine Werke / 000 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
BKL-Classification:54 Informatik / 54.72 Künstliche Intelligenz
54 Informatik / 54.74 Maschinelles Sehen
Licence (German):License Logo Creative Commons 4.0 - Namensnennung-Nicht kommerziell (CC BY-NC 4.0)