Road Crack Detection Using Deep Neural Network Based on Attention Mechanism and Residual Structure

Abstract

Intelligent detection of road cracks is crucial for road maintenance and safety. Due to the interference of illumination and different background factors, the road crack extraction results of existing deep learning methods are incomplete, and the extraction accuracy is low. We designed a new network model, called AR-UNet, which introduces a convolutional block attention module (CBAM) in the encoder and decoder of U-Net to effectively extract global and local detail information. The input and output CBAM features of the model are connected to increase the transmission path of features.The BasicBlock is adopted to replace the convolutional layer of the original network to avoid network degradation caused by gradient disappearance and network layer growth. We tested our method on DeepCrack, Crack Forest Dataset, and our own labeled road image dataset (RID). The experimental results show that our method focuses more on crack feature information and extracts cracks with higher integrity. The comparison with existing deep learning methods also demonstrates the effectiveness of our proposed method. The code is available at: https://github.com/18435398440/ARUnet.

Data-driven approach for AI-based crack detection: techniques, challenges, and future scope

“…The results show that the proposed method outperforms other methods regarding experimental precision. Jing et al (2022) proposed the AR-UNet network model to improve further the accuracy of crack detection, which introduces a convolutional block attention module (CBAM) in the encoder and decoder of the U-Net. The CBAM allows for effectively extracting global and local detail information, while the basic block prevents network degradation and layer growth.…”

Comprehensive Review on Plant Disease Detection and Identification

“…Even though the fundamental CNN architectures-AlexNet, VGGNet, GoogLeNet, DenseNet, as well as ResNet-have been used extensively in the classification of plant diseases, they have a number of limitations, such as the requirement for a large number of the parameters and a slow estimation speed. While deep learning techniques have demonstrated remarkable proficiency in exhibiting both high-level as well as low-level features, their consistency in that describes local spatial characteristics is lacking [25].Fusion Approaches to Image Segmentation • On older leaves, patterns of concentric zonation may indicate the necrotic center of the spots.…”

An End-to-End Computer Vision System Based on Deep Learning for Pavement Distress Detection and Quantification

“…This model is an encoder-decoder architecture where the main innovations are the use of Swin transformers and window-based self-attention mechanisms. Jing et al [27] built an UNet with convolutional block attention mechanisms to improve the extraction ability on fine cracks.…”