Comprehensive, Quantitative Crack Detection Algorithm Performance Evaluation System

Tsai, Yichang; Chatterjee, Anirban

doi:10.1061/(asce)cp.1943-5487.0000696

Cited by 21 publications

(14 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attention gates (AGs) are a vital tool that has been demonstrated to be a game changer in deep learning. They are frequently utilized in tasks such as classification [26,27], machine translation [28], knowledge graphs, natural image analysis [29], and natural language processing (NLP) for image captioning [30]. Attention mechanisms have been used in deep learning, particularly in computer vision, to solve a wide range of problems, including image segmentation [31,32] action recognition [26], image classification [26,33], and image captioning [34].…”

Section: Attention Gatesmentioning

confidence: 99%

“…For the input tensors, channel-wise 1 × 1 × 1 convolutions are used to compute the linear transformations [30]. As vector concatenation-based attention [35], the concatenated features x and g are linearly transferred to a R F int dimensional intermediate space.…”

Section: Parameter Selectionsmentioning

confidence: 99%

“…For accurate comparison with our results, we ran experiments using the same equipment and platform environment, as well as both the Dashboard image dataset and the Roadway fractures dataset. We employed evaluation criteria such as positive predictive value (PPV) [37], true positive rate (TPR), F1, and Hausdorff distance score (HD-score) [30,38] to assess the accuracy of crack detection, since many related researchers employed these criteria to evaluate the performance of the proposed algorithms [1,3,[9][10][11]15,16,19,21]. Moreover, we will employ more criteria to evaluate the performance of our method in future studies.…”

Section: Evaluation Metricmentioning

confidence: 99%

See 2 more Smart Citations

Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks

Kyslytsyna

Xia

Kislitsyn³

et al. 2021

Sensors

View full text Add to dashboard Cite

Constant monitoring of road surfaces helps to show the urgency of deterioration or problems in the road construction and to improve the safety level of the road surface. Conditional generative adversarial networks (cGAN) are a powerful tool to generate or transform the images used for crack detection. The advantage of this method is the highly accurate results in vector-based images, which are convenient for mathematical analysis of the detected cracks at a later time. However, images taken under established parameters are different from images in real-world contexts. Another potential problem of cGAN is that it is difficult to detect the shape of an object when the resulting accuracy is low, which can seriously affect any further mathematical analysis of the detected crack. To tackle this issue, this paper proposes a method called improved cGAN with attention gate (ICGA) for roadway surface crack detection. To obtain a more accurate shape of the detected target object, ICGA establishes a multi-level model with independent stages. In the first stage, everything except the road is treated as noise and removed from the image. These images are stored in a new dataset. In the second stage, ICGA determines the cracks. Therefore, ICGA focuses on the redistribution of cracks, not the auxiliary elements in the image. ICGA adds two attention gates to a U-net architecture and improves the segmentation capacities of the generator in pix2pix. Extensive experimental results on dashboard camera images of the Unsupervised Llamas dataset show that our method has better performance than other state-of-the-art methods.

show abstract

Section: Attention Gatesmentioning

confidence: 99%

Section: Parameter Selectionsmentioning

confidence: 99%

Section: Evaluation Metricmentioning

confidence: 99%

See 1 more Smart Citation

Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks

Kyslytsyna

Xia

Kislitsyn³

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Wang et al [19] and Kong and Yang [20] analyzed that the working resistance of the support should meet the requirements of the coal wall. Some evaluation and analysis methods are also used in engineering evaluation [21][22][23][24], and it is used to predict and evaluate support life based on the mechanical structure damage [25,26], and it is used to evaluate quantitatively the system performance to get the performance level [27,28]. Du [29] adopted the fuzzy comprehensive analysis method to establish the evaluation model to deal with a series of fuzzy factors affecting the working condition of the support.…”

Section: Introductionmentioning

confidence: 99%

Multifactor Evaluation of Multiple Service Support and Optimization of Working Resistance of New Support Based on Dynamic Pressure

et al. 2020

Shock and Vibration

View full text Add to dashboard Cite

The scientific and feasible method is extremely important for the evaluation of whether the support of coal mines needs to be scrapped, but it has not been formed. If the support cannot be continued to use, the determined reasonable working resistance of the support before the primary mining of coal seam should be optimized. Based on the field measurement and theoretical analysis, the concept of the actual rated working resistance of the support is proposed and analyzed accurately; the total amount of roof subsidence of circulating multiple coal cutting cycles during periodic pressure is calculated; the support performance is evaluated by multifactors; a new method for determining the reasonable working resistance of the support based on dynamic pressure is proposed. The study found that the safety valve of support is opened in advance and the resistance loss rate is large; the total amount of roof subsidence during periodic pressure is high; FAHP + EWM evaluation score of support system performance is 63.31 points. The scientific evaluation of multifactors showed that the support has reached service life, and as a result, the new 105 working faces required replacement with new support. The reasonable working resistance of the support in the 3-1 coal seam is optimized according to the new method based on dynamic pressure. This study can greatly improve the safety of roof control in the working face.

show abstract

“…In the field, crack detection algorithms are subjected to different pavement types, various lighting conditions and noise that it may not be designed to handle. [17] elaborates on this problem and presents a standardized performance evaluation system for crack detection algorithms.…”

Section: Lack Of a Performance Metricmentioning

confidence: 99%

Challenges and lessons from the successful implementation of automated road condition surveys on a large highway system

Tsai

Chatterjee

Jiang

2017

2017 25th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

Abstract-Signal processing based automated road condition surveys (ARCS) system are the solution for the current unsafe, subjective and labor-intensive manual road condition surveys. Although extensive research has been conducted on methods for ARCS, application by transportation agencies is still minimal. In 2016, an ARCS system, developed by Georgia Tech, was successfully implemented on a 4,184km highway system in Georgia, USA. This paper presents the insights gained from the project and also discusses the remaining challenges with a focus on crack detection and classification. Crack fundamental elements were implemented to obtain a flexible multi-scale output. A combination of ARCS and QA/QC tools were used to obtain high accuracy results while minimizing human effort. Gaps in ARCS research, such as the lack of a crack detection algorithm performance measure were revealed. The solutions and new challenges revealed from this study will help ARCS researchers to create solutions which can be readily applied by transportation agencies.

show abstract

Comprehensive, Quantitative Crack Detection Algorithm Performance Evaluation System

Cited by 21 publications

References 24 publications

Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks

Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks

Multifactor Evaluation of Multiple Service Support and Optimization of Working Resistance of New Support Based on Dynamic Pressure

Challenges and lessons from the successful implementation of automated road condition surveys on a large highway system

Contact Info

Product

Resources

About