PPDD: Egocentric Crack Segmentation in the Port Pavement with Deep Learning-Based Methods

Road infrastructure is a critical component of modern society, with its maintenance directly influencing traffic safety and logistical efficiency. In this context, automated crack detection technology plays a vital role in reducing maintenance costs and enhancing operational efficiency. However, pre...

Full description

Saved in:
Bibliographic Details
Main Authors: Hyemin Yoon, Hoe-Kyoung Kim, Sangjin Kim
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/10/5446
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850258161353621504
author Hyemin Yoon
Hoe-Kyoung Kim
Sangjin Kim
author_facet Hyemin Yoon
Hoe-Kyoung Kim
Sangjin Kim
author_sort Hyemin Yoon
collection DOAJ
description Road infrastructure is a critical component of modern society, with its maintenance directly influencing traffic safety and logistical efficiency. In this context, automated crack detection technology plays a vital role in reducing maintenance costs and enhancing operational efficiency. However, previous studies are limited by the fact that they provide only bounding box or segmentation mask annotations for a restricted number of crack classes and use a relatively small size of datasets. To address these limitations and advance deep learning-based crack segmentation, this study introduces a novel crack segmentation dataset that reflects real-world road conditions. The proposed dataset includes various types of cracks and defects—such as slippage, rutting, and construction-related cracks—and provides polygon-based segmentation masks captured from an egocentric, vehicle-mounted perspective. Using this dataset, we evaluated the performance of semantic and instance segmentation models. Notably, SegFormer achieved the highest Pixel Accuracy (PA) and mean Intersection over Union (mIoU) for semantic segmentation, while YOLOv7 exhibited outstanding detection performance for alligator crack class, recording an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>A</mi><mi>P</mi></mrow><mrow><mn>50</mn></mrow></msub></mrow></semantics></math></inline-formula> of 87.2% and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> of 57.5%. In contrast, all models struggled with the reflection crack type, indicating the inherent segmentation challenges. Overall, this study provides a practical and robust foundation for future research in automated road crack segmentation. Additional resources including the dataset and annotation details can be found at our GitHub repository.
format Article
id doaj-art-31fe3e28a85b4cc19ac18cca8dc769bb
institution OA Journals
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-31fe3e28a85b4cc19ac18cca8dc769bb2025-08-20T01:56:14ZengMDPI AGApplied Sciences2076-34172025-05-011510544610.3390/app15105446PPDD: Egocentric Crack Segmentation in the Port Pavement with Deep Learning-Based MethodsHyemin Yoon0Hoe-Kyoung Kim1Sangjin Kim2Department of Management Information Systems, Dong-A University, Busan 49236, Republic of KoreaDepartment of Urban Planning and Engineering, Dong-A University, Busan 49315, Republic of KoreaDepartment of Management Information Systems, Dong-A University, Busan 49236, Republic of KoreaRoad infrastructure is a critical component of modern society, with its maintenance directly influencing traffic safety and logistical efficiency. In this context, automated crack detection technology plays a vital role in reducing maintenance costs and enhancing operational efficiency. However, previous studies are limited by the fact that they provide only bounding box or segmentation mask annotations for a restricted number of crack classes and use a relatively small size of datasets. To address these limitations and advance deep learning-based crack segmentation, this study introduces a novel crack segmentation dataset that reflects real-world road conditions. The proposed dataset includes various types of cracks and defects—such as slippage, rutting, and construction-related cracks—and provides polygon-based segmentation masks captured from an egocentric, vehicle-mounted perspective. Using this dataset, we evaluated the performance of semantic and instance segmentation models. Notably, SegFormer achieved the highest Pixel Accuracy (PA) and mean Intersection over Union (mIoU) for semantic segmentation, while YOLOv7 exhibited outstanding detection performance for alligator crack class, recording an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>A</mi><mi>P</mi></mrow><mrow><mn>50</mn></mrow></msub></mrow></semantics></math></inline-formula> of 87.2% and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> of 57.5%. In contrast, all models struggled with the reflection crack type, indicating the inherent segmentation challenges. Overall, this study provides a practical and robust foundation for future research in automated road crack segmentation. Additional resources including the dataset and annotation details can be found at our GitHub repository.https://www.mdpi.com/2076-3417/15/10/5446semantic segmentationinstance segmentationdeep learningport road crackvehicle-egocentric view datadata analysis
spellingShingle Hyemin Yoon
Hoe-Kyoung Kim
Sangjin Kim
PPDD: Egocentric Crack Segmentation in the Port Pavement with Deep Learning-Based Methods
Applied Sciences
semantic segmentation
instance segmentation
deep learning
port road crack
vehicle-egocentric view data
data analysis
title PPDD: Egocentric Crack Segmentation in the Port Pavement with Deep Learning-Based Methods
title_full PPDD: Egocentric Crack Segmentation in the Port Pavement with Deep Learning-Based Methods
title_fullStr PPDD: Egocentric Crack Segmentation in the Port Pavement with Deep Learning-Based Methods
title_full_unstemmed PPDD: Egocentric Crack Segmentation in the Port Pavement with Deep Learning-Based Methods
title_short PPDD: Egocentric Crack Segmentation in the Port Pavement with Deep Learning-Based Methods
title_sort ppdd egocentric crack segmentation in the port pavement with deep learning based methods
topic semantic segmentation
instance segmentation
deep learning
port road crack
vehicle-egocentric view data
data analysis
url https://www.mdpi.com/2076-3417/15/10/5446
work_keys_str_mv AT hyeminyoon ppddegocentriccracksegmentationintheportpavementwithdeeplearningbasedmethods
AT hoekyoungkim ppddegocentriccracksegmentationintheportpavementwithdeeplearningbasedmethods
AT sangjinkim ppddegocentriccracksegmentationintheportpavementwithdeeplearningbasedmethods