HDFA-YOLO: A real-time steel surface defect detection model based on backbone lightweight design and multi-scale feature fusion
Authors:
- Jie LiJLJie Li
- Xuan HeXHXuan He
- Xiao ChenXCXiao Chen
- Dehao KongDKDehao Kong
- Taihong HuangTHTaihong Huang
- Peng SongPSPeng Song
- 22 October 2025
- journal article
- Published by Elsevier in Measurement
- Vol. 258
Abstract
No abstract availableFunding Information
- Yunnan Key Research and Development Program
- Yunnan Provincial Science and Technology Department (202401CF070146, 2024J0076, 202303AP140016, 202302AB080003)
- Yunnan Provincial Department of Education Science Research Fund Project
This publication has 37 references indexed in Scilit:
- A real-time and efficient surface defect detection method based on YOLOv4Journal of Real-Time Image Processing, 2023
- A supervised approach for automated surface defect detection in ceramic tile quality controlAdvanced Engineering Informatics, 2022
- Surface defect detection of steel strips based on improved YOLOv4Computers and Electrical Engineering, 2022
- A lightweight detector based on attention mechanism for aluminum strip surface defect detectionComputers in Industry, 2022
- Temporal synchronization framework of machine-vision cameras for high-speed steel surface inspection systemsJournal of Real-Time Image Processing, 2022
- A modified-YOLOv5s model for detection of wire braided hose defectsMeasurement, 2022
- Mask-RCNN with spatial attention for pedestrian segmentation in cyber–physical systemsComputer Communications, 2021
- Defect detection method for rail surface based on line-structured lightMeasurement, 2020
- Occlusion-Aware R-CNN: Detecting Pedestrians in a Crowd2018
- SSD: Single Shot MultiBox Detector2016