TY - JOUR
T1 - Automatic Pavement Crack Detection Based on Octave Convolution Neural Network with Hierarchical Feature Learning
AU - Xu, Minggang
AU - Li, Chong
AU - Chen, Ying
AU - Wei, Wu
N1 - Publisher Copyright:
© 2024 Beijing Institute of Technology. All rights reserved.
PY - 2024
Y1 - 2024
N2 - Automatic pavement crack detection plays an important role in ensuring road safety. In images of cracks, information about the cracks can be conveyed through high-frequency and low-frequency signals that focus on fine details and global structures, respectively. The output features obtained from different convolutional layers can be combined to represent information about both high-frequency and low-frequency signals. In this paper, we propose an encoder-decoder framework called octave hierarchical network (Octave-H), which is based on the U-Network (U-Net) architecture and utilizes an octave convolutional neural network and a hierarchical feature learning module for performing crack detection. The proposed octave convolution is capable of extracting multi-frequency feature maps, capturing both fine details and global cracks. We propose a hierarchical feature learning module that merges multi-frequency-scale feature maps with different levels (high and low) of octave convolutional layers. To verify the superiority of the proposed Octave-H, we employed the CrackForest dataset (CFD) and AigleRN databases to evaluate this method. The experimental results demonstrate that Octave-H outperforms other algorithms with satisfactory performance.
AB - Automatic pavement crack detection plays an important role in ensuring road safety. In images of cracks, information about the cracks can be conveyed through high-frequency and low-frequency signals that focus on fine details and global structures, respectively. The output features obtained from different convolutional layers can be combined to represent information about both high-frequency and low-frequency signals. In this paper, we propose an encoder-decoder framework called octave hierarchical network (Octave-H), which is based on the U-Network (U-Net) architecture and utilizes an octave convolutional neural network and a hierarchical feature learning module for performing crack detection. The proposed octave convolution is capable of extracting multi-frequency feature maps, capturing both fine details and global cracks. We propose a hierarchical feature learning module that merges multi-frequency-scale feature maps with different levels (high and low) of octave convolutional layers. To verify the superiority of the proposed Octave-H, we employed the CrackForest dataset (CFD) and AigleRN databases to evaluate this method. The experimental results demonstrate that Octave-H outperforms other algorithms with satisfactory performance.
KW - automated pavement crack detection
KW - hierarchical feature
KW - multifrequency
KW - multiscale
KW - octave convolutional network
UR - http://www.scopus.com/inward/record.url?scp=85215755894&partnerID=8YFLogxK
U2 - 10.15918/j.jbit1004-0579.2024.056
DO - 10.15918/j.jbit1004-0579.2024.056
M3 - Article
AN - SCOPUS:85215755894
SN - 1004-0579
VL - 33
SP - 422
EP - 435
JO - Journal of Beijing Institute of Technology (English Edition)
JF - Journal of Beijing Institute of Technology (English Edition)
IS - 5
ER -