An Improved YOLOv8 Algorithm for Rail Surface Defect Detection
To tackle the issues raised by detecting small targets and densely occluded targets in railroad track surface defect detection, we present an algorithm for detecting defects on railroad tracks based on the YOLOv8 model. Firstly, we enhance the model’s attention towards small and medium-si...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10477344/ |
_version_ | 1797231216389259264 |
---|---|
author | Yan Wang Kehua Zhang Ling Wang Lintong Wu |
author_facet | Yan Wang Kehua Zhang Ling Wang Lintong Wu |
author_sort | Yan Wang |
collection | DOAJ |
description | To tackle the issues raised by detecting small targets and densely occluded targets in railroad track surface defect detection, we present an algorithm for detecting defects on railroad tracks based on the YOLOv8 model. Firstly, we enhance the model’s attention towards small and medium-sized targets by substituting replacing the original convolution with the SPD-Conv building block in the backbone network of YOLOv8n, while preserving the original network structure. Secondly, we integrate the EMA attention mechanism module into the neck component, allowing the model to leverage information from different layers of features and improve feature representation capabilities. Lastly, we substitute the original C-IOU with the Focal-SIoU loss function in YOLOv8, which adjusts the weights of positive and negative samples to penalize difficult-to-classify samples more heavily. This enhancement improves the model’s capability to accurately recognize challenging samples and ensures that the network allocates greater attention to each target instance, resulting in improved performance and effectiveness of the model. The experimental results reveal notable advancements in precision, recall, and average accuracy attained by our enhanced algorithm. Compared to the original YOLOv8n model, our enhanced algorithm demonstrates remarkable precision, recall, and average accuracy of 93.9%, 93.7%, and 94.1%, respectively. These improvements amount to 3.6%, 5.0%, and 5.7%, respectively. Notably, these enhancements are accomplished while maintaining the dimensions of the model and the parameter count. During the identification of defects on railroad track surfaces, our improved algorithm surpasses other widely used algorithms in terms of performance. |
first_indexed | 2024-04-24T15:40:51Z |
format | Article |
id | doaj.art-95c5429a07894680b7de02cdcf5f2c3c |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-24T15:40:51Z |
publishDate | 2024-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-95c5429a07894680b7de02cdcf5f2c3c2024-04-01T23:00:30ZengIEEEIEEE Access2169-35362024-01-0112449844499710.1109/ACCESS.2024.338000910477344An Improved YOLOv8 Algorithm for Rail Surface Defect DetectionYan Wang0Kehua Zhang1https://orcid.org/0000-0001-9623-3949Ling Wang2Lintong Wu3School of Engineering, Zhejiang Normal University, Jinhua, ChinaKey Laboratory of Urban Rail Transit Intelligent Operation and Maintenance Technology and Equipment of Zhejiang Province, Zhejiang Normal University, Jinhua, ChinaSchool of Engineering, Zhejiang Normal University, Jinhua, ChinaKey Laboratory of Urban Rail Transit Intelligent Operation and Maintenance Technology and Equipment of Zhejiang Province, Zhejiang Normal University, Jinhua, ChinaTo tackle the issues raised by detecting small targets and densely occluded targets in railroad track surface defect detection, we present an algorithm for detecting defects on railroad tracks based on the YOLOv8 model. Firstly, we enhance the model’s attention towards small and medium-sized targets by substituting replacing the original convolution with the SPD-Conv building block in the backbone network of YOLOv8n, while preserving the original network structure. Secondly, we integrate the EMA attention mechanism module into the neck component, allowing the model to leverage information from different layers of features and improve feature representation capabilities. Lastly, we substitute the original C-IOU with the Focal-SIoU loss function in YOLOv8, which adjusts the weights of positive and negative samples to penalize difficult-to-classify samples more heavily. This enhancement improves the model’s capability to accurately recognize challenging samples and ensures that the network allocates greater attention to each target instance, resulting in improved performance and effectiveness of the model. The experimental results reveal notable advancements in precision, recall, and average accuracy attained by our enhanced algorithm. Compared to the original YOLOv8n model, our enhanced algorithm demonstrates remarkable precision, recall, and average accuracy of 93.9%, 93.7%, and 94.1%, respectively. These improvements amount to 3.6%, 5.0%, and 5.7%, respectively. Notably, these enhancements are accomplished while maintaining the dimensions of the model and the parameter count. During the identification of defects on railroad track surfaces, our improved algorithm surpasses other widely used algorithms in terms of performance.https://ieeexplore.ieee.org/document/10477344/Rail defects detectiondeep learningYOLOv8convolution moduleattention mechanismloss function |
spellingShingle | Yan Wang Kehua Zhang Ling Wang Lintong Wu An Improved YOLOv8 Algorithm for Rail Surface Defect Detection IEEE Access Rail defects detection deep learning YOLOv8 convolution module attention mechanism loss function |
title | An Improved YOLOv8 Algorithm for Rail Surface Defect Detection |
title_full | An Improved YOLOv8 Algorithm for Rail Surface Defect Detection |
title_fullStr | An Improved YOLOv8 Algorithm for Rail Surface Defect Detection |
title_full_unstemmed | An Improved YOLOv8 Algorithm for Rail Surface Defect Detection |
title_short | An Improved YOLOv8 Algorithm for Rail Surface Defect Detection |
title_sort | improved yolov8 algorithm for rail surface defect detection |
topic | Rail defects detection deep learning YOLOv8 convolution module attention mechanism loss function |
url | https://ieeexplore.ieee.org/document/10477344/ |
work_keys_str_mv | AT yanwang animprovedyolov8algorithmforrailsurfacedefectdetection AT kehuazhang animprovedyolov8algorithmforrailsurfacedefectdetection AT lingwang animprovedyolov8algorithmforrailsurfacedefectdetection AT lintongwu animprovedyolov8algorithmforrailsurfacedefectdetection AT yanwang improvedyolov8algorithmforrailsurfacedefectdetection AT kehuazhang improvedyolov8algorithmforrailsurfacedefectdetection AT lingwang improvedyolov8algorithmforrailsurfacedefectdetection AT lintongwu improvedyolov8algorithmforrailsurfacedefectdetection |