Title :
A novel crack detection algorithm of underwater dam image
Author :
Cong-ping Chen ; Jian Wang ; Lei Zou ; Jun Fu ; Cong-ji Ma
Author_Institution :
Sch. of Mech. & Mater. Eng., Three Gorges Univ., Yichang, China
Abstract :
A novel algorithm is introduced for the deficiencies of underwater dam image crack detection. The algorithm makes use of the intensity values of 2D image to generate a 3D spatial surface, which is regarded as a concave-convex ground with “pits” and “ditches”. The “pits” represent the noise pixels and the “ditches” represent the crack pixels. The cracks that are difficult to describe in 2D image can be regarded well as ditches in the 3D spatial surface. Then by analyzing the characteristics of ditches space curvatures, the space detected method is used to get the ditches information, which is mapped to 2D surface as the crack. Because the detected result contains some noise and fake cracks, so BP neural network is adopted to identify crack object. As a result, the crack information is detected successfully.
Keywords :
backpropagation; crack detection; dams; image processing; neural nets; object detection; structural engineering computing; 2D image; 3D spatial surface; BP neural network; concave-convex ground; crack detection algorithm; crack object identification; crack pixels; ditches space curvatures; noise pixels; underwater dam image; Detection algorithms; Feature extraction; Hydroelectric power generation; Neural networks; Noise; Surface cracks; Surface morphology; BP neural network; crack recognition; space curvature; underwater dam image;
Conference_Titel :
Systems and Informatics (ICSAI), 2012 International Conference on
Conference_Location :
Yantai
Print_ISBN :
978-1-4673-0198-5
DOI :
10.1109/ICSAI.2012.6223399
