Concrete pavement defects are an important indicator reflecting the safety status of pavement. However, it is difficult to accurately detect the concrete pavement cracks due to the complex concrete pavement environment, such as uneven illumination, deformation and potential shadows, etc. In order to solve these problems, we propose the crack detection algorithm of concrete pavement with convolutional neural network. Firstly, our method is used to classify cracks first and detect the classified crack images, different deep learning models are used in these two parts to achieve different functions. Secondly, in the crack classification section, in view of the low proportion of effective concrete pavement crack images in the mass images collected by crack detection vehicle, the output dimension of FC2 layer of LeNet-5 model is modified before crack detection. It can accurately identify the concrete pavement cracks from several types of disturbance characteristics by training the classification model. Finally, in order to improve the efficiency of crack detection, the algorithm scales the network model horizontally and accesses the convolution layer with the kernel size of 1×1, 3×3. Experiments show that the 1 F of our algorithm reaches to 0.896 in CFD dataset. Compared with VGG16, U-Net and Percolation, it is 25.2%, 2.8%, 39.1% improvement of 1 F respectively. For Cracktree200 dataset, the 1 F is 0.892. Compared with VGG16, U-Net and Percolation, it is 50.3%, 16.6%, 68.9% improvement of 1 F respectively. For DeepCrack dataset, the 1 F is 0.901. Compared with VGG16, U-Net and Percolation, it is 53%, 5.2%, 52.2% improvement of 1 F respectively.

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.

Crack detection for concrete pavement is an important and fundamental task to ensure road safety. However, automatic crack detection is a challenging topic due to the complicated concrete pavement background and the diversity of cracks. Inspired by the latest developments of deep learning in computer vision, we propose a novel crack detection algorithm of concrete pavement based on attention mechanism and multi-features fusion, and make it possible to deal with various cracks in different pavement backgrounds. The proposed network is constructed using the encoder-decoder structure. The architecture of the encoder part is consisted of Res2Net modules with attention mechanism to achieve fast focus of cracks. Cascade and parallel mode dilated convolutions are set as the center part to enlarge the receptive field of feature points without reducing the resolution of the feature maps. The decoder integrates multiple side output feature maps for pavement crack detection in the manner of feature pyramid. We use ODS, OIS and AP to evaluate the performance of our network. To demonstrate the validity and accuracy of the proposed method, we compare it with some existing methods. The experimental results in multiple crack datasets reveal that our method is superior to these methods.

Automatically detecting cracks with uneven strength from a complex background is a valuable and challenging issue. In light of the lost details and the incomplete extracted cracks in the process of crack extraction, we propose a network model with hierarchical feature fusion and connected attention architecture. Firstly, we build the backbone network on the improved DCA-SE-ResNet-50. Then, we propose a method for crack feature fusion, which combines depthwise separable convolution and dilated convolution to recover more crack details. Finally, we design the attention layer which integrates feature map2 with feature map4. The side network incorporates the feature maps of the low convolutional layer and the high convolutional layer at multiple levels to assist in obtaining the final prediction map. Sufficient experimental results demonstrate that our method achieved state-of-the-art performances, best F-score over 0.86, 12 FPS. Besides the effectiveness of our proposed method is verified on CFD, Crack500, and DCD datasets.

Suffering from the diversity, complexity, and miniaturization of printed circuit board (PCB) defects, traditional detection methods are difficult to detect. Despite object detection has made significant advances based on deep neural networks, it remains a challenge to focus on small objects. We address this challenge by allowing multiscale fusion. We introduce a PCB defect detection algorithm based on extended feature pyramid network model in this article. The backbone is constructed by part of ResNet-101, in order to accurately locate and identify small objects, this article constructs a feature layer, which integrates high-level semantic information and low-level geometric information. Based on feature pyramid networks (FPN) network structure, using $1\times1$ convolution lateral fusion of the previous semantic information, the fused features use $3\times3$ convolution to obtain the final feature layer. The problem that PCB defects are difficult to classify is considered, the focal loss function is introduced. To reduce over-fitting in the training process, the original data are enhanced using image clipping and rotation. Through the quantitative analysis on PCB defect dataset, these results are the best to be used in fused low-level feature layer for detection of the mean average precision (mAP). This is 96.2% on the public PCB dataset, which is surpassing the state-of-the-art methods.