A Deeply Supervised Convolutional Neural Network for Pavement Crack Detection With Multiscale Feature Fusion

• Published in: IEEE transaction on neural networks and learning systems Vol. 33; no. 9; pp. 4890 - 4899
• Main Authors: Qu, Zhong, Cao, Chong, Liu, Ling, Zhou, Dong-Yang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Convolution; Convolutional neural networks; Convolutional neural networks (CNNs); deep supervision; Edge detection; Explosives detection; Feature extraction; Image edge detection; Image processing; Image segmentation; Learning systems; Modules; multiscale feature fusion; Neural networks; pavement crack detection; Road maintenance; Semantics; Training
• DOI: 10.1109/TNNLS.2021.3062070
• ISSN: 2162-237X; 2162-2388

Automatic crack detection is vital for efficient and economical road maintenance. With the explosive development of convolutional neural networks (CNNs), recent crack detection methods are mostly based on CNNs. In this article, we propose a deeply supervised convolutional neural network for crack detection via a novel multiscale convolutional feature fusion module. Within this multiscale feature fusion module, the high-level features are introduced directly into the low-level features at different convolutional stages. Besides, deep supervision provides integrated direct supervision for convolutional feature fusion, which is helpful to improve model convergency and final performance of crack detection. Multiscale convolutional features learned at different convolution stages are fused together to robustly represent cracks, whose geometric structures are complicated and hardly captured by single-scale features. To demonstrate its superiority and generalizability, we evaluate the proposed network on three public crack data sets, respectively. Sufficient experimental results demonstrate that our method outperforms other state-of-the-art crack detection, edge detection, and image segmentation methods in terms of F1-score and mean IU.