SDDNet: Real-Time Crack Segmentation

• Published in: IEEE transactions on industrial electronics (1982) Vol. 67; no. 9; pp. 8016 - 8025
• Main Authors: Choi, Wooram, Cha, Young-Jin
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Computational efficiency; Computer architecture; Convolution; Crack segmentation; Damage detection; Decoding; deep learning (DL); Feature extraction; Image segmentation; Machine learning; Modules; Real time; Real-time systems; separable convolution; structural health monitoring (SHM)

This article reports the development of a pure deep learning method for segmenting concrete cracks in images. The objectives are to achieve the real-time performance while effectively negating a wide range of various complex backgrounds and crack-like features. To achieve the goals, an original conv...