Patch-Based Crack Detection in Black Box Images Using Convolutional Neural Networks

Park, Somin; Bang, Su Sik; Kim, Hongjo; Kim, Hyoungkwan

doi:10.1061/(asce)cp.1943-5487.0000831

Cited by 103 publications

(31 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…VGG16 and VGG19 are the popular versions with 16 and 19 layers, and 138 and 144 million parameters, respectively. [32,34,102,141,144,145,176,178,[186][187][188][189][190][191][192][193][194] Inception (Inception-V2, V3, V4) 1 [19,181,195] •…”

Section: Transfer Learning (Tl) Through Pre-trained Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review

Azimi

Eslamlou

Pekcan

2020

Sensors

334

158

View full text Add to dashboard Cite

Data-driven methods in structural health monitoring (SHM) is gaining popularity due to recent technological advancements in sensors, as well as high-speed internet and cloud-based computation. Since the introduction of deep learning (DL) in civil engineering, particularly in SHM, this emerging and promising tool has attracted significant attention among researchers. The main goal of this paper is to review the latest publications in SHM using emerging DL-based methods and provide readers with an overall understanding of various SHM applications. After a brief introduction, an overview of various DL methods (e.g., deep neural networks, transfer learning, etc.) is presented. The procedure and application of vibration-based, vision-based monitoring, along with some of the recent technologies used for SHM, such as sensors, unmanned aerial vehicles (UAVs), etc. are discussed. The review concludes with prospects and potential limitations of DL-based methods in SHM applications.

show abstract

Section: Transfer Learning (Tl) Through Pre-trained Modelsmentioning

confidence: 99%

“…Post-disaster inspection • Comprehensive maintenance and inspection for bridges [143,157,169,178,196,198,202] MobileNet • Road damage detection [173] UNet, SegCaps, SegNet [113] • Segmentation • Pixel-level crack detection [186,194] ZF-net [187] • ZF-Net for fast R-CNN. CrackNet, CrackNet-R [139,188] •…”

Section: Crack Detention •mentioning

confidence: 99%

Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review

Azimi

Eslamlou

Pekcan

2020

Sensors

334

158

View full text Add to dashboard Cite

show abstract

“…How to characterize the time-varying dependency between different failure modes is still robust, especially in multi-component systems. In the future, deep learning-based methods, e.g., the convolutional neural network [86], as well as the long short-term memory neural network [87], may be helpful in extracting useful information and identifying different failure processes from performance degradation data.…”

Section: C: Statistical Acceleration Modelmentioning

confidence: 99%

Modeling and Analysis of Performance Degradation Data for Reliability Assessment: A Review

Chen

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Reliability engineering plays an important role in the design, manufacture, maintenance, and replacement of industrial products. Over the last few decades, accelerated degradation testing (ADT) has been largely utilized to shorten test durations, reduce the samples needed, and provide sufficient degradation data to ensure the effective reliability assessment of the concerned products. Meanwhile, performance degradation modeling has been recognized as an essential approach to help researchers and producers understand the health conditions of the deteriorating systems. However, the diversity in reliability tests, degradation models, and statistical analysis techniques has increased the difficulty in selecting appropriate reliability assessment methods in specific scenarios. Besides, there are no systematic reviews focused on modeling and analysis of performance degradation data. Therefore, this paper aims to (1) present ADT fundamentals, including the basic theory, ADT methods, accelerated stress variables, type of acceleration models, as well as ADT optimization, (2) comprehensively review current states and future challenges in degradation modeling, (3) discuss the problem of model mis-specification and compare different approaches for parameter estimation, (4) highlight future opportunities and possible directions deserving further research.

show abstract

“…Thus, DCNN can potentially alleviate the issue from subjective parameter selection and outperform the traditional approaches, given that the data samples used in DCNN are diversified and representative of the actual scenarios. Majority of current DCNN-based crack classification methodologies 37–42 adopted raw intensity image data for analysis. Nevertheless, some other applications adopted pre-processing techniques such as intensity correction and thresholding, 43 image binarization and noise removal, 44 and image smoothing 45 to address the issues in intensity images prior to applying DCNN.…”

Section: Introductionmentioning

confidence: 99%

Deep learning–based roadway crack classification with heterogeneous image data fusion

Zhou

Song

2020

Structural Health Monitoring

View full text Add to dashboard Cite

By providing accurate and efficient crack detection and localization, image-based crack detection methodologies can facilitate the decision-making and rehabilitation of the roadway infrastructure. Deep convolutional neural network, as one of the most prevailing image-based methodologies on object recognition, has been extensively adopted for crack classification tasks in the recent decade. For most of the current deep convolutional neural network–based techniques, either intensity or range image data are utilized to interpret the crack presence. However, the complexities in real-world data may impair the robustness of deep convolutional neural network architecture in its ability to analyze image data with various types of disturbances, such as low contrast in intensity images and shallow cracks in range images. The detection performance under these disturbances is important to protect the investment in infrastructure, as it can reveal the trend of crack evolution and provide information at an early stage to promote precautionary measures. This article proposes novel deep convolutional neural network–based roadway classification tools and investigates their performance from the perspective of using heterogeneous image fusion. A vehicle-mounted laser imaging system is adopted for data acquisition (DAQ) on concrete roadways with a depth resolution of 0.1 mm and an accuracy of 0.4 mm. In total, four types of image data including raw intensity, raw range, filtered range, and fused raw image data are utilized to train and test the deep convolutional neural network architectures proposed in this study. The experimental cases demonstrate that the proposed data fusion approach can reduce false detections and thus results in an improvement of 4.5%, 1.2%, and 0.7% in the F-measure value, respectively, compared to utilizing the raw intensity, raw range, and filtered range image data for analysis. Furthermore, in another experimental case, two novel deep convolutional neural network architectures proposed in this study are compared to exploit the fused raw image data, and the one leading to better classification performance is determined.

show abstract

Patch-Based Crack Detection in Black Box Images Using Convolutional Neural Networks

Cited by 103 publications

References 30 publications

Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review

Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review

Modeling and Analysis of Performance Degradation Data for Reliability Assessment: A Review

Deep learning–based roadway crack classification with heterogeneous image data fusion

Contact Info

Product

Resources

About