Hierarchical Convolutional Neural Network With Feature Preservation and Autotuned Thresholding for Crack Detection

• Published in: IEEE access Vol. 9; pp. 60201 - 60214
• Main Authors: Zhu, Qiuchen, Dinh, Tran Hiep, Phung, Manh Duong, Ha, Quang Phuc
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Bridge inspection; Computational modeling; Convolutional neural networks; crack detection; Datasets; Deep learning; Feature extraction; Feature maps; feature preserving; Hazardous areas; hierarchical convolutional neural network; Image processing; Inspection; Iterative methods; Kernel; Machine learning; Machine vision; Monorails; Neural networks; Occultation; Post-production processing; Surface cracks; Surface defects; thresholding; Unmanned aerial vehicles

Drone imagery is increasingly used in automated inspection for infrastructure surface defects, especially in hazardous or unreachable environments. In machine vision, the key to crack detection rests with robust and accurate algorithms for image processing. To this end, this paper proposes a deep le...