Learning to Detect Cracks on Damaged Concrete Surfaces Using Two-Branched Convolutional Neural Network

• Published in: Sensors (Basel, Switzerland) Vol. 19; no. 21; p. 4796
• Main Authors: Lee, Jieun, Kim, Hee-Sun, Kim, Nayoung, Ryu, Eun-Mi, Kang, Je-Won
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 04.11.2019; MDPI
• Subjects: Algorithms; Classification; Concrete; Concrete structures; Convolution; convolutional neural network; crack detection; Cracks; Damage detection; Deep learning; edge detection; fire-damaged concrete; Flaw detection; image processing; Morphology; Neural networks; Noise; Nuclear power plants; Semantics; Sensors; image processing; deep learning; fire-damaged concrete; edge detection; crack detection; convolutional neural network

Image sensors are widely used for detecting cracks on concrete surfaces to help proactive and timely management of concrete structures. However, it is a challenging task to reliably detect cracks on damaged surfaces in the real world due to noise and undesired artifacts. In this paper, we propose an...