Automatic Pixel-Level Crack Detection on Dam Surface Using Deep Convolutional Network

• Published in: Sensors (Basel, Switzerland) Vol. 20; no. 7; p. 2069
• Main Authors: Feng, Chuncheng, Zhang, Hua, Wang, Haoran, Wang, Shuang, Li, Yonglong
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 07.04.2020; MDPI
• Subjects: Accuracy; Algorithms; Concrete; crack detection; Cracks; dam surface; deep convolutional network; Deep learning; Hydroelectric power; Machine learning; Neural networks; Nuclear power plants; pixel-level; Semantics; Support vector machines; UAV; pixel-level; dam surface; deep convolutional network; UAV; crack detection

Crack detection on dam surfaces is an important task for safe inspection of hydropower stations. More and more object detection methods based on deep learning are being applied to crack detection. However, most of the methods can only achieve the classification and rough location of cracks. Pixel-le...