A Photovoltaic Image Crack Detection Algorithm Based on Laplacian Pyramid Decomposition

2019 ◽  
pp. 604-611
Author(s):  
Dai Sui ◽  
Dongqing Cui
Keyword(s):  
Crack Detection ◽  
Detection Algorithm ◽  
Laplacian Pyramid

scholarly journals Concrete Crack Detection Based on Well-Known Feature Extractor Model and the YOLO_v2 Network

2021 ◽  
Vol 11 (2) ◽  
pp. 813
Author(s):  
Shuai Teng ◽  
Zongchao Liu ◽  
Gongfa Chen ◽  
Li Cheng
Keyword(s):  
Feature Extraction ◽  
Crack Detection ◽  
Computational Cost ◽  
Concrete Structures ◽  
Detection Algorithm ◽  
Computational Time ◽  
Image Size ◽  
Important Indicator ◽  
Feature Extractor ◽  
Model Training

This paper compares the crack detection performance (in terms of precision and computational cost) of the YOLO_v2 using 11 feature extractors, which provides a base for realizing fast and accurate crack detection on concrete structures. Cracks on concrete structures are an important indicator for assessing their durability and safety, and real-time crack detection is an essential task in structural maintenance. The object detection algorithm, especially the YOLO series network, has significant potential in crack detection, while the feature extractor is the most important component of the YOLO_v2. Hence, this paper employs 11 well-known CNN models as the feature extractor of the YOLO_v2 for crack detection. The results confirm that a different feature extractor model of the YOLO_v2 network leads to a different detection result, among which the AP value is 0.89, 0, and 0 for ‘resnet18’, ‘alexnet’, and ‘vgg16’, respectively meanwhile, the ‘googlenet’ (AP = 0.84) and ‘mobilenetv2’ (AP = 0.87) also demonstrate comparable AP values. In terms of computing speed, the ‘alexnet’ takes the least computational time, the ‘squeezenet’ and ‘resnet18’ are ranked second and third respectively; therefore, the ‘resnet18’ is the best feature extractor model in terms of precision and computational cost. Additionally, through the parametric study (influence on detection results of the training epoch, feature extraction layer, and testing image size), the associated parameters indeed have an impact on the detection results. It is demonstrated that: excellent crack detection results can be achieved by the YOLO_v2 detector, in which an appropriate feature extractor model, training epoch, feature extraction layer, and testing image size play an important role.

Fatigue Crack Propagation Behavior and Degradation Characteristics of STS316L by Nondestructive Evaluation

2005 ◽  
Vol 297-300 ◽  
pp. 2016-2021
Author(s):  
So Soon Park ◽  
Seok Hwan Ahn ◽  
Chang Kwon Moon ◽  
Ki Woo Nam
Keyword(s):  
Crack Detection ◽  
New Technology ◽  
Signal Amplitude ◽  
Detection Algorithm ◽  
Source Location ◽  
Patch Type ◽  
Fatigue Crack Propagation Behavior ◽  
Existing Structures ◽  
Propagation Behavior ◽  
Evaluation Algorithm

Structural health monitoring (SHM) is a new technology that has been increasingly evaluated by the industry as a potential approach to improve the cost and ease of structural inspection. Piezoelectric smart active layer (SAL) sensor was fabricated to verify the applicability of finding cracks and conducting source location in a various materials. A crack detection and source location works were done in three kinds of test condition such as aluminum plates with crack for patch type SAL sensor, a smart airplane with embedding SAL sensor, and a concrete beam with real crack for practical application. From this experimental study, the evaluation algorithm for the arrival time delay and decrease of signal amplitude was suggested in this paper. Consequently, it was found that the SAL sensor and detection algorithm developed in this study can be effectively used to detect and monitor damages in the both existing structures and new designed smart structures.

A Novel Pavement Crack Detection Algorithm Using Interlaced Low-Rank Group Convolution Hybrid Deep Network Under a Complex Background

2020 ◽  
Vol 57 (14) ◽  
pp. 141031
Author(s):  
李刚 Li Gang ◽  
刘强伟 Liu Qiangwei ◽  
万健 Wan Jian ◽  
马彪 Ma Biao ◽  
李莹 Li Ying
Keyword(s):  
Crack Detection ◽  
Detection Algorithm ◽  
Low Rank ◽  
Deep Network ◽  
Complex Background ◽  
Pavement Crack Detection ◽  
Rank Group

scholarly journals Learning to Detect Cracks on Damaged Concrete Surfaces Using Two-Branched Convolutional Neural Network

Sensors ◽  
2019 ◽  
Vol 19 (21) ◽  
pp. 4796
Author(s):  
Jieun Lee ◽  
Hee-Sun Kim ◽  
Nayoung Kim ◽  
Eun-Mi Ryu ◽  
Je-Won Kang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Real World ◽  
Crack Detection ◽  
Region Of Interest ◽  
Detection Algorithm ◽  
Image Sensors ◽  
Final Output ◽  
Gradient Component ◽  
Functional Components

Image sensors are widely used for detecting cracks on concrete surfaces to help proactive and timely management of concrete structures. However, it is a challenging task to reliably detect cracks on damaged surfaces in the real world due to noise and undesired artifacts. In this paper, we propose an autonomous crack detection algorithm based on convolutional neural network (CNN) to solve the problem. To this aim, the proposed algorithm uses a two-branched CNN architecture, consisting of sub-networks named a crack-component-aware (CCA) network and a crack-region-aware (CRA) network. The CCA network is to learn gradient component regarding cracks, and the CRA network is to learn a region-of-interest by distinguishing critical cracks and noise such as scratches. Specifically, the two sub-networks are built on convolution-deconvolution CNN architectures, but also they are comprised of different functional components to achieve their own goals efficiently. The two sub-networks are trained in an end-to-end to jointly optimize parameters and produce the final output of localizing important cracks. Various crack image samples and learning methods are used for efficiently training the proposed network. In the experimental results, the proposed algorithm provides better performance in the crack detection than the conventional algorithms.

A research on an improved Unet-based concrete crack detection algorithm

2020 ◽  
pp. 147592172094006
Author(s):  
Lingxin Zhang ◽  
Junkai Shen ◽  
Baijie Zhu
Keyword(s):  
Deep Learning ◽  
Crack Detection ◽  
Detection Algorithm ◽  
Important Indicator ◽  
Test Dataset ◽  
Training Time ◽  
Damage Level ◽  
Detection Algorithms ◽  
Concrete Crack ◽  
Model Affect

Crack is an important indicator for evaluating the damage level of concrete structures. However, traditional crack detection algorithms have complex implementation and weak generalization. The existing crack detection algorithms based on deep learning are mostly window-level algorithms with low pixel precision. In this article, the CrackUnet model based on deep learning is proposed to solve the above problems. First, crack images collected from the lab, earthquake sites, and the Internet are resized, labeled manually, and augmented to make a dataset (1200 subimages with 256 × 256 × 3 resolutions in total). Then, an improved Unet-based method called CrackUnet is proposed for automated pixel-level crack detection. A new loss function named generalized dice loss is adopted to detect cracks more accurately. How the size of the dataset and the depth of the model affect the training time, detecting accuracy, and speed is researched. The proposed methods are evaluated on the test dataset and a previously published dataset. The highest results can reach 91.45%, 88.67%, and 90.04% on test dataset and 98.72%, 92.84%, and 95.44% on CrackForest Dataset for precision, recall, and F1 score, respectively. By comparing the detecting accuracy, the training time, and the information of datasets, CrackUnet model outperform than other methods. Furthermore, six images with complicated noise are used to investigate the robustness and generalization of CrackUnet models.

scholarly journals Research on Crack Detection Algorithm of the Concrete Bridge Based on Image Processing

2019 ◽  
Vol 154 ◽  
pp. 610-616 ◽  
Author(s):  
Yun Wang ◽  
Ju Yong Zhang ◽  
Jing Xin Liu ◽  
Yin Zhang ◽  
Zhi Ping Chen ◽  
...  
Keyword(s):  
Image Processing ◽  
Crack Detection ◽  
Detection Algorithm ◽  
Concrete Bridge

scholarly journals Detection of Micro-Cracks in Metals Using Modulation of PZT-Induced Lamb Waves

Materials ◽  
2020 ◽  
Vol 13 (17) ◽  
pp. 3823
Author(s):  
Sang Eon Lee ◽  
Jung-Wuk Hong
Keyword(s):  
Quantitative Analysis ◽  
Crack Length ◽  
Crack Detection ◽  
Lamb Waves ◽  
Early Stage ◽  
Fatigue Cracks ◽  
Excitation Frequency ◽  
High Sensitivity ◽  
Detection Algorithm ◽  
Modulated Waves

The ultrasonic modulation technique, developed by inspecting the nonlinearity from the interactions of crack surfaces, has been considered very effective in detecting fatigue cracks in the early stage of the crack development due to its high sensitivity. The wave modulation is the frequency shift of a wave passing through a crack and does not occur in intact specimens. Various parameters affect the modulation of the wave, but quantitative analysis for each variable has not been comprehensively conducted due to the complicated interaction of irregular crack surfaces. In this study, specimens with a constant crack width are manufactured, and the effects of various excitation parameters on modulated wave generation are analyzed. Based on the analysis, an effective crack detection algorithm is proposed and verified by applying the algorithm to fatigue cracks. For the quantitative analysis, tests are repeatedly conducted by varying parameters. As a result, the excitation intensity shows a strong linear relationship with the amount of modulated waves, and the increase of modulated wave is expected as crack length increases. However, the change in the dynamic characteristics of the specimen with the crack length is more dominant in the results. The excitation frequency is the most dominant variable to generate the modulated waves, but a direct correlation is not observed as it is difficult to measure the interaction of crack surfaces. A numerical analysis technique is developed to accurately simulate the movement and interaction of the crack surface. The crack detection algorithm, improved by using the observations from the quantitative analyses, can distinguish the occurrence of modulated waves from the ambient noises, and the state of the specimens is determined by using two nonlinear indexes.

SOM and RBF Networks for Eddy Current Nondestructive Testing

2011 ◽  
Vol 219-220 ◽  
pp. 1093-1096 ◽  
Author(s):  
Bing Liu ◽  
Ai Hua Li ◽  
Chang Long Wang ◽  
Jian Bin Wang ◽  
Ye Teng Ni
Keyword(s):  
Nondestructive Testing ◽  
Eddy Current ◽  
Crack Detection ◽  
Detection Algorithm ◽  
Ratio Method ◽  
Test Scheme ◽  
Self Organizing Maps ◽  
Rbf Network ◽  
Fisher Ratio ◽  
Som Network

Eddy current testing is a popular nondestructive testing (NDT) technology with a solid theoretical foundation. This paper presents a new crack test scheme which uses a self-organizing maps (SOM) network and a radial basis function (RBF) network to process the crack feature signals in eddy current NDT. And Fisher ratio method is adopted to optimize the RBF network centers and simplifies the network structure. The validity of this crack detection algorithm is verified by an experiment in which the wave signals of different crack locations and depths are acquired from the simulations and used as the training and testing samples. Finally, the assessment of the network’s accuracy is performed and the result is satisfactory.

Sign in / Sign up

Export Citation Format

Share Document