Pothole Classification Model Using Edge Detection in Road Image

Baek, Jiwon; Chung, Kyungyong

doi:10.3390/app10196662

Cited by 44 publications

(15 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They used a semisupervised learning approach to conduct road pavement hazard detection. Moreover, Baek et al [22] proposed a pothole classification model using edge detection and a YOLO-based feature extraction scheme for pothole detection. However, these studies have only considered ideal situations such as daytime on a sunny day.…”

Section: Related Workmentioning

confidence: 99%

Implementation of Pavement Defect Detection System on Edge Computing Platform

2021

View full text Add to dashboard Cite

Road surfaces in Taiwan, as well as other developed countries, often experience structural failures, such as patches, bumps, longitudinal and lateral cracking, and potholes, which cause discomfort and pose direct safety risks to motorists. To minimize damage to vehicles from pavement defects or provide the corresponding comfortable ride promotion strategy later, in this study, we developed a pavement defect detection system using a deep learning perception scheme for implementation on Xilinx Edge AI platforms. To increase the detection distance and accuracy of pavement defects, two cameras with different fields of view, at 70∘ and 30∘, respectively, were used to capture the front views of a car, and then the YOLOv3 (you only look once, version 3) model was employed to recognize the pavement defects, such as potholes, cracks, manhole covers, patches, and bumps. In addition, to promote continuous pavement defect recognition rate, a tracking-via-detection strategy was employed, which first detects pavement defects in each frame and then associates them to different frames using the Kalman filter method. Thus, the average detection accuracy of the pothole category could reach 71%, and the miss rate was about 29%. To confirm the effectiveness of the proposed detection strategy, experiments were conducted on an established Taiwan pavement defect image dataset (TPDID), which is the first dataset for Taiwan pavement defects. Moreover, different AI methods were used to detect the pavement defects for quantitative comparative analysis. Finally, a field-programmable gate-array-based edge computing platform was used as an embedded system to implement the proposed YOLOv3-based pavement defect detection system; the execution speed reached 27.8 FPS while maintaining the accuracy of the original system model.

show abstract

Section: Related Workmentioning

confidence: 99%

Implementation of Pavement Defect Detection System on Edge Computing Platform

2021

View full text Add to dashboard Cite

show abstract

“…Along with that, there has been active research on data analysis for predicting results using reinforcement learning and machine learning based on different data comprising numbers, images, videos, etc., and the subsequent extraction of significant information. Data analysis methods have differences depending on their purpose [2]. For example, the regression analysis method is applied to analyze causal relations between dependent and independent variables.…”

Section: Introductionmentioning

confidence: 99%

Multi-Context Mining-Based Graph Neural Network for Predicting Emerging Health Risks

Baek

Chung

2023

IEEE Access

View full text Add to dashboard Cite

Patients with similar diseases are able to have similar treatments, care, symptoms, and causes. Based on these relations, it is possible to predict latent risks. Therefore, this study proposes Graph Neural Network-based Multi-Context mining for predicting emerging health risks. The proposed method collects and pre-processes chronic disease patients' disease information, behavioral pattern information, and mental health information. After that, it performs context mining. This is a multivariate regression analysis for predicting multiple dependent variables, it extracts a regression model and generates a feature map. Then, the initial graph is created by defining the number of clusters as nodes and constructing edges through correlation. By expanding the graph according to the results of context mining, it is possible to predict that a user has a similar chronic disorder and similar symptoms through users' connection relations. For performance evaluation, the validity of the regression analysis of context mining used in the proposed method, and the suitability of the clustering technique are evaluated.

show abstract

“…Current methods for evaluating road quality involve performing inspection with specialized equipment to assess pavement condition and ride quality [ 7 , 8 , 9 , 10 , 11 ]. Some studies have used image processing techniques to estimate IRI and detect potholes [ 12 , 13 , 14 , 15 , 16 , 17 ]. Recent initiatives use LiDAR for pavement inspection because it can provide additional information on roadway drainage, pavement markings, and lane widths [ 18 , 19 , 20 , 21 , 22 , 23 , 24 ].…”

Section: Introductionmentioning

confidence: 99%

Pavement Quality Evaluation Using Connected Vehicle Data

Mahlberg

Zachrisson³

et al. 2022

Sensors

View full text Add to dashboard Cite

Modern vehicles have extensive instrumentation that can be used to actively assess the condition of infrastructure such as pavement markings, signs, and pavement smoothness. Currently, pavement condition evaluations are performed by state and federal officials typically using the industry standard of the International Roughness Index (IRI) or visual inspections. This paper looks at the use of on-board sensors integrated in Original Equipment Manufacturer (OEM) connected vehicles to obtain crowdsource estimates of ride quality using the International Rough Index (IRI). This paper presents a case study where over 112 km (70 mi) of Interstate-65 in Indiana were assessed, utilizing both an inertial profiler and connected production vehicle data. By comparing the inertial profiler to crowdsourced connected vehicle data, there was a linear correlation with an R2 of 0.79 and a p-value of <0.001. Although there are no published standards for using connected vehicle roughness data to evaluate pavement quality, these results suggest that connected vehicle roughness data is a viable tool for network level monitoring of pavement quality.

show abstract

Pothole Classification Model Using Edge Detection in Road Image

Cited by 44 publications

References 46 publications

Implementation of Pavement Defect Detection System on Edge Computing Platform

Implementation of Pavement Defect Detection System on Edge Computing Platform

Multi-Context Mining-Based Graph Neural Network for Predicting Emerging Health Risks

Pavement Quality Evaluation Using Connected Vehicle Data

Contact Info

Product

Resources

About