A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Performance of artificial intelligence approach on bridge coating assessment
Digital image processing has been prevalently adopted in different areas. In the construction field, image processing has been used for defect detection on steel bridge painting and underground sewer systems. However, non-uniformly illuminated images always cause recognition problems and affect the accuracy. In order to resolve these problems, the neuro-fuzzy recognition approach (NFRA) was proposed. The NFRA segments an image into three areas based on illumination and conducts area-based thresholding. The neural network is used in this approach for automatic generation of three threshold values, with the three average illumination values of the three areas as the input. The fuzzy adjustment is utilized to smooth and adjust the gray level values of the image pixels along the boundaries. In this paper, the framework of NFRA and the rationale of the fuzzy adjustment will be presented, followed by the comparison of the recognition results using NFRA and the multi-resolution pattern classification (MPC) method. The result shows that the proposed NFRA performs fairly well on recognizing rust images. Finally, the conclusions will be drawn.
Performance of artificial intelligence approach on bridge coating assessment
Digital image processing has been prevalently adopted in different areas. In the construction field, image processing has been used for defect detection on steel bridge painting and underground sewer systems. However, non-uniformly illuminated images always cause recognition problems and affect the accuracy. In order to resolve these problems, the neuro-fuzzy recognition approach (NFRA) was proposed. The NFRA segments an image into three areas based on illumination and conducts area-based thresholding. The neural network is used in this approach for automatic generation of three threshold values, with the three average illumination values of the three areas as the input. The fuzzy adjustment is utilized to smooth and adjust the gray level values of the image pixels along the boundaries. In this paper, the framework of NFRA and the rationale of the fuzzy adjustment will be presented, followed by the comparison of the recognition results using NFRA and the multi-resolution pattern classification (MPC) method. The result shows that the proposed NFRA performs fairly well on recognizing rust images. Finally, the conclusions will be drawn.
Performance of artificial intelligence approach on bridge coating assessment
Leistung eines künstliche-Intelligenz-Verfahrens für die Bewertung von Brückenbelägen
Chen, P.H. (author) / Chang, L.M. (author)
2002
6 Seiten, 11 Bilder, 1 Tabelle, 7 Quellen
Conference paper
English
Artificial intelligence application to bridge painting assessment
| British Library Online Contents | 2003
Artificial intelligence application to bridge painting assessment
| Online Contents | 2003
Artificial intelligence application to bridge painting assessment
| Elsevier | 2003
Hybrid Artificial Intelligence Approach to Continuous Bridge Monitoring
| British Library Online Contents | 1995
Artificial Intelligence in Bridge Engineering
| Online Contents | 1996