Refine
Document Type
- Report (4)
- Article (2)
- Doctoral Thesis (1)
Keywords
- Handy (4)
- Museumsführer (4)
- Neuronales Netz (4)
- Objekterkennung (4)
- Museum (3)
- Objektverfolgung (3)
- mobile phones (3)
- museum guidance (3)
- object recognition (3)
- Anpassung (2)
- Bilderkennung (2)
- museum guidance system (2)
- neural networks (2)
- pervasive tracking (2)
- Ad-hoc Sensor-Netzwerke (1)
- Ad-hoc-Netz (1)
- Adaptive Klassifizierung (1)
- Bildverarbeitung (1)
- Bluetooth tracking (1)
- CAMShift (1)
- GPU Programming (1)
- Kernel-Based Tracking (1)
- Kontextbezogenes System (1)
- Maschinelles Sehen (1)
- Mobile Computing (1)
- Mobiltelefone (1)
- Museum Guidance (1)
- Neural Networks (1)
- Peer-to-Peer-Netz (1)
- Phone-to-phone communication (1)
- PhoneGuide (1)
- Positionsbestimmung (1)
- Räumliche Beziehungen (1)
- Smartphone (1)
- Spatial Relationships (1)
- Subobject Detection (1)
- Subobjekterkennung (1)
- Ubiquitous Computing (1)
- Wegrouten (1)
- ad-hoc sensor networks (1)
- adaptive classification (1)
- adaptive image classification (1)
- mobile ad-hoc networks (1)
- pathway awareness (1)
- temporal adaptation (1)
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 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.