scholarly journals Automatic Pixel-Level Pavement Crack Recognition Using a Deep Feature Aggregation Segmentation Network with a scSE Attention Mechanism Module

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2902
Author(s):  
Wenting Qiao ◽  
Qiangwei Liu ◽  
Xiaoguang Wu ◽  
Biao Ma ◽  
Gang Li
Keyword(s):  
Deep Learning ◽  
Crack Detection ◽  
Attention Mechanism ◽  
Model Parameters ◽  
Detection Accuracy ◽  
Safe Driving ◽  
Deep Feature ◽  
Feature Aggregation ◽  
Pavement Crack Detection ◽  
Detection Speed

Pavement crack detection is essential for safe driving. The traditional manual crack detection method is highly subjective and time-consuming. Hence, an automatic pavement crack detection system is needed to facilitate this progress. However, this is still a challenging task due to the complex topology and large noise interference of crack images. Recently, although deep learning-based technologies have achieved breakthrough progress in crack detection, there are still some challenges, such as large parameters and low detection efficiency. Besides, most deep learning-based crack detection algorithms find it difficult to establish good balance between detection accuracy and detection speed. Inspired by the latest deep learning technology in the field of image processing, this paper proposes a novel crack detection algorithm based on the deep feature aggregation network with the spatial-channel squeeze & excitation (scSE) attention mechanism module, which calls CrackDFANet. Firstly, we cut the collected crack images into 512 × 512 pixel image blocks to establish a crack dataset. Then through iterative optimization on the training and validation sets, we obtained a crack detection model with good robustness. Finally, the CrackDFANet model verified on a total of 3516 images in five datasets with different sizes and containing different noise interferences. Experimental results show that the trained CrackDFANet has strong anti-interference ability, and has better robustness and generalization ability under the interference of light interference, parking line, water stains, plant disturbance, oil stains, and shadow conditions. Furthermore, the CrackDFANet is found to be better than other state-of-the-art algorithms with more accurate detection effect and faster detection speed. Meanwhile, our algorithm model parameters and error rates are significantly reduced.

scholarly journals Pavement Crack Detection Method Based on Deep Learning Models

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Guo X. Hu ◽  
Bao L. Hu ◽  
Zhong Yang ◽  
Li Huang ◽  
Ping Li
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Crack Detection ◽  
Detection Method ◽  
Longitudinal Crack ◽  
Detection Accuracy ◽  
Safe Driving ◽  
Detection Model ◽  
Model Based ◽  
Pavement Crack Detection

Severe weather and long-term driving of vehicles lead to various cracks on asphalt pavement. If these cracks cannot be found and repaired in time, it will have a negative impact on the safe driving of vehicles. Traditional artificial detection has some problems, such as low efficiency and missing detection. The detection model based on machine learning needs artificial design of pavement crack characteristics. According to the pavement distress identification manual proposed by the Federal Highway Administration (FHWA), these categories have three different types of cracks, such as fatigue, longitudinal crack, and transverse cracks. In the face of many types of pavement cracks, it is difficult to design a general feature extraction model to extract pavement crack features, which leads to the poor effect of the automatic detection model based on machine learning. Object detection based on the deep learning model has achieved good results in many fields. As a result, those models have become possible for pavement crack detection. This paper discusses the latest YOLOv5 series detection model for pavement crack detection and is to find out an effective training and detection method. Firstly, the 3001 asphalt crack pavement images with the original size of 2976 × 3978 pixels are collected using a digital camera and are randomly divided into three types according to the severity levels of low, medium, and high. Then, for the dataset of crack pavement, YOLOv5 series models are used for training and testing. The experimental results show that the detection accuracy of the YOLOv5l model is the highest, reaching 88.1%, and the detection time of the YOLOv5s model is the shortest, only 11.1 ms for each image.

scholarly journals Application of Color Featuring and Deep Learning in Maize Plant Detection

2020 ◽  
Vol 12 (14) ◽  
pp. 2229
Author(s):  
Haojie Liu ◽  
Hong Sun ◽  
Minzan Li ◽  
Michihisa Iida
Keyword(s):  
Deep Learning ◽  
False Negative ◽  
Color Space ◽  
Performance Comparison ◽  
Maize Plant ◽  
Detection Accuracy ◽  
Learning Technology ◽  
Practical Applications ◽  
Feature Based ◽  
Detection Speed

Maize plant detection was conducted in this study with the goals of target fertilization and reduction of fertilization waste in weed spots and gaps between maize plants. The methods used included two types of color featuring and deep learning (DL). The four color indices used were excess green (ExG), excess red (ExR), ExG minus ExR, and the hue value from the HSV (hue, saturation, and value) color space, while the DL methods used were YOLOv3 and YOLOv3_tiny. For practical application, this study focused on performance comparison in detection accuracy, robustness to complex field conditions, and detection speed. Detection accuracy was evaluated by the resulting images, which were divided into three categories: true positive, false positive, and false negative. The robustness evaluation was performed by comparing the average intersection over union of each detection method across different sub–datasets—namely original subset, blur processing subset, increased brightness subset, and reduced brightness subset. The detection speed was evaluated by the indicator of frames per second. Results demonstrated that the DL methods outperformed the color index–based methods in detection accuracy and robustness to complex conditions, while they were inferior to color feature–based methods in detection speed. This research shows the application potential of deep learning technology in maize plant detection. Future efforts are needed to improve the detection speed for practical applications.

Deep Learning–Based Fully Automated Pavement Crack Detection on 3D Asphalt Surfaces with an Improved CrackNet

2018 ◽  
Vol 32 (5) ◽  
pp. 04018041 ◽  
Author(s):  
Allen Zhang ◽  
Kelvin C. P. Wang ◽  
Yue Fei ◽  
Yang Liu ◽  
Siyu Tao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Crack Detection ◽  
Pavement Crack Detection

scholarly journals A New Video-Based Crash Detection Method: Balancing Speed and Accuracy Using a Feature Fusion Deep Learning Framework

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Zhenbo Lu ◽  
Wei Zhou ◽  
Shixiang Zhang ◽  
Chen Wang
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Feature Fusion ◽  
Urban Traffic ◽  
Detection Accuracy ◽  
Traffic Crash ◽  
Learning Framework ◽  
Proposed Model ◽  
Speed And Accuracy ◽  
Detection Speed

Quick and accurate crash detection is important for saving lives and improved traffic incident management. In this paper, a feature fusion-based deep learning framework was developed for video-based urban traffic crash detection task, aiming at achieving a balance between detection speed and accuracy with limited computing resource. In this framework, a residual neural network (ResNet) combined with attention modules was proposed to extract crash-related appearance features from urban traffic videos (i.e., a crash appearance feature extractor), which were further fed to a spatiotemporal feature fusion model, Conv-LSTM (Convolutional Long Short-Term Memory), to simultaneously capture appearance (static) and motion (dynamic) crash features. The proposed model was trained by a set of video clips covering 330 crash and 342 noncrash events. In general, the proposed model achieved an accuracy of 87.78% on the testing dataset and an acceptable detection speed (FPS > 30 with GTX 1060). Thanks to the attention module, the proposed model can capture the localized appearance features (e.g., vehicle damage and pedestrian fallen-off) of crashes better than conventional convolutional neural networks. The Conv-LSTM module outperformed conventional LSTM in terms of capturing motion features of crashes, such as the roadway congestion and pedestrians gathering after crashes. Compared to traditional motion-based crash detection model, the proposed model achieved higher detection accuracy. Moreover, it could detect crashes much faster than other feature fusion-based models (e.g., C3D). The results show that the proposed model is a promising video-based urban traffic crash detection algorithm that could be used in practice in the future.

scholarly journals A Hybrid Crack Detection Approach for Scanning Electron Microscope Image Using Deep Learning Method

Scanning ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Lun Zhao ◽  
Yunlong Pan ◽  
Sen Wang ◽  
Liang Zhang ◽  
Md Shafiqul Islam
Keyword(s):  
Deep Learning ◽  
Electron Microscope ◽  
Scanning Electron Microscope ◽  
Crack Detection ◽  
Rapid Development ◽  
Detection Accuracy ◽  
Learning Method ◽  
Sem Images ◽  
Bounding Boxes ◽  
Scanning Electron

The scanning electron microscope (SEM) is widely used in the analysis and research of materials, including fracture analysis, microstructure morphology, and nanomaterial analysis. With the rapid development of materials science and computer vision technology, the level of detection technology is constantly improving. In this paper, the deep learning method is used to intelligently identify microcracks in the microscopic morphology of SEM image. A deep learning model based on image level is selected to reduce the interference of other complex microscopic topography, and a detection method with dense continuous bounding boxes suitable for SEM images is proposed. The dense and continuous bounding boxes were used to obtain the local features of the cracks and rotating the bounding boxes to reduce the feature differences between the bounding boxes. Finally, the bounding boxes with filled regression were used to highlight the microcrack detection effect. The results show that the detection accuracy of our approach reached 71.12%, and the highest mIOU reached 64.13%. Also, microcracks in different magnifications and in different backgrounds were detected successfully.

scholarly journals Attention-Based Convolutional Neural Network for Pavement Crack Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Haifeng Wan ◽  
Lei Gao ◽  
Manman Su ◽  
Qirun Sun ◽  
Lei Huang
Keyword(s):  
Loss Function ◽  
Crack Detection ◽  
Contextual Information ◽  
Activation Function ◽  
Detection Accuracy ◽  
The Public ◽  
Lighting Conditions ◽  
Public Dataset ◽  
The Mean ◽  
Pavement Crack Detection

Achieving high detection accuracy of pavement cracks with complex textures under different lighting conditions is still challenging. In this context, an encoder-decoder network-based architecture named CrackResAttentionNet was proposed in this study, and the position attention module and channel attention module were connected after each encoder to summarize remote contextual information. The experiment results demonstrated that, compared with other popular models (ENet, ExFuse, FCN, LinkNet, SegNet, and UNet), for the public dataset, CrackResAttentionNet with BCE loss function and PRelu activation function achieved the best performance in terms of precision (89.40), mean IoU (71.51), recall (81.09), and F1 (85.04). Meanwhile, for a self-developed dataset (Yantai dataset), CrackResAttentionNet with BCE loss function and PRelu activation function also had better performance in terms of precision (96.17), mean IoU (83.69), recall (93.44), and F1 (94.79). In particular, for the public dataset, the precision of BCE loss and PRelu activation function was improved by 3.21. For the Yantai dataset, the results indicated that the precision was improved by 0.99, the mean IoU was increased by 0.74, the recall was increased by 1.1, and the F1 for BCE loss and PRelu activation function was increased by 1.24.

scholarly journals An Encoder-decoder Deep Learning Model Combining Mixed Attention Mechanism and Asymmetric Convolution for Automation of Retinal Vessels Segmentation

2021 ◽  
Author(s):  
Jiajia Cao ◽  
Qin Zhou ◽  
Yi Chen ◽  
Lin Yin ◽  
Fei Zhang
Keyword(s):  
Deep Learning ◽  
Attention Mechanism ◽  
Model Parameters ◽  
Network Architectures ◽  
Retinal Vessels ◽  
Model Combining ◽  
Equal Importance ◽  
Segmentation Methods ◽  
Public Datasets ◽  
Learned Features

The segmentation of the retinal vascular tree is the fundamental step for diagnosing ophthalmological diseases and cardiovascular diseases. Most existing vessel segmentation methods based on deep learning give the learned features equal importance. Ignored the highly imbalanced ratio between background and vessels (the majority of vessel pixels belong to the background), the learned features would be dominantly guided by background, and relatively little influence comes from vessels, often leading to low model sensitivity and prediction accuracy. The reduction of model size is also a challenge. We propose a mixed attention mechanism and asymmetric convolution encoder-decoder structure(MAAC) for segmentation in Retinal Vessels to solve these problems. In MAAC, the mixed attention is designed to emphasize the valid features and suppress the invalid features. It not only identifies information that helps retinal vessels recognition but also locates the position of the vessel. All square convolutions are replaced by asymmetric convolutions because it is more robust to rotational distortions and small convolutions are more suitable for extracting vessel features (based on the thin characteristics of vessels). The employment of asymmetric convolution reduces model parameters and improve the recognition of thin vessel. The experiments on public datasets DRIVE, STARE, and CHASE\_DB1 demonstrated that the proposed MAAC could more accurately segment vessels with a global AUC of 98.17$\%$, 98.67$\%$, and 98.53$\%$, respectively. The mixed attention proposed in this study can be applied to other deep learning models for performance improvement without changing the network architectures. <br>

scholarly journals Three-Dimensional Asphalt Pavement Crack Detection Based on Fruit Fly Optimisation Density Peak Clustering

2019 ◽  
Vol 2019 ◽  
pp. 1-15 ◽  
Author(s):  
Wei Li ◽  
Ranran Deng ◽  
Yingjie Zhang ◽  
Zhaoyun Sun ◽  
Xueli Hao ◽  
...  
Keyword(s):  
Crack Detection ◽  
Clustering Algorithm ◽  
Asphalt Pavement ◽  
Fruit Fly ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Density Peak ◽  
3D Data ◽  
Density Peak Clustering ◽  
Pavement Crack Detection

Complex pavement texture and noise impede the effectiveness of existing 3D pavement crack detection methods. To improve pavement crack detection accuracy, we propose a 3D asphalt pavement crack detection algorithm based on fruit fly optimisation density peak clustering (FO-DPC). Firstly, the 3D data of asphalt pavement are collected, and a 3D image acquisition system is built using Gocator3100 series binocular intelligent sensors. Then, the fruit fly optimisation algorithm is adopted to improve the density peak clustering algorithm. Clustering analysis that can accurately detect cracks is performed on the height characteristics of the 3D data of the asphalt pavement. Finally, the clustering results are projected onto a 2D space and compared with the results of other 2D crack detection methods. Following this comparison, it is established that the proposed algorithm outperforms existing methods in detecting asphalt pavement cracks.

Sign in / Sign up

Export Citation Format

Share Document