Naslov
A knowledge-based system for the non-destructive diagnostics of façade isolation using the information fusion of visual and IR images

Autori
Ribarić, Slobodan ; Marčetić, Darijan ; Vedrina, Denis Stjepan

Izvornik
Expert Systems with Applications (0957-4174) 36 (2009), 2 Part 2; 3812-3823

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Knowledge-based system; Non-destructive diagnostic; Information fusion; Multispectral analysis

Sažetak
This paper describes a knowledge-based system for the non-destructive diagnostics of façade isolation. The system uses the fusion of information extracted from images obtained from two electromagnetic wavebands: from low-resolution IR images (320 x 240 pixels ; 7.5– 13 mm wavelength), and from high-resolution visual RGB images (3264 x 2448 pixels ; 0.39– 0.75 mm wavelength). The fusion of the information is a perquisite for the design of an efficient knowledge-based system for non-destructive testing and façade diagnostics. In the paper, special attention is devoted to the following knowledge-based system components: application-specific components (image acquisition, the resolution pyramid, image pre-processing and feature extraction, image registration, object segmentation, fusion, and data analysis) and system-core components (the database, the knowledge base, the inference engine, and the user interface). Examples of the non-destructive testing and the façade diagnostics obtained with the system are presented.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

Napomena
Submitted: 5 September 2007 ; Available online 5 March 2008

POVEZANOST RADA