A Lightweight Strip Steel Surface Defect Detection Network Based on Improved YOLOv8.

Sensors (Basel)

School of Physics and Electronic Engineering, Harbin Normal University, Harbin 150025, China.

Published: October 2024

AI Article Synopsis

  • Strip steel surface defect detection is essential for maintaining quality in steel production, but existing algorithms struggle with accuracy and speed due to varying defect sizes and blurred images.
  • The proposed solution, YOLO-SDS, is a lightweight network that enhances the original YOLOv8 model by implementing a new backbone (StarNet) and incorporating advanced modules for better multi-scale feature extraction and handling occluded objects.
  • Experimental results indicate that YOLO-SDS reduces model parameters by 34.4% while increasing detection accuracy by 1.5%, demonstrating significant advantages in efficiency over other defect detection models.

Article Abstract

Strip steel surface defect detection has become a crucial step in ensuring the quality of strip steel production. To address the issues of low detection accuracy and long detection times in strip steel surface defect detection algorithms caused by varying defect sizes and blurred images during acquisition, this paper proposes a lightweight strip steel surface defect detection network, YOLO-SDS, based on an improved YOLOv8. Firstly, StarNet is utilized to replace the backbone network of YOLOv8, achieving lightweight optimization while maintaining accuracy. Secondly, a lightweight module DWR is introduced into the neck and combined with the C2f feature extraction module to enhance the model's multi-scale feature extraction capability. Finally, an occlusion-aware attention mechanism SEAM is incorporated into the detection head, enabling the model to better capture and process features of occluded objects, thus improving performance in complex scenarios. Experimental results on the open-source NEU-DET dataset show that the improved model reduces parameters by 34.4% compared with the original YOLOv8 algorithm while increasing average detection accuracy by 1.5%. And it shows good generalization performance on the deepPCB dataset. Compared with other defect detection models, YOLO-SDS offers significant advantages in terms of parameter count and detection speed. Additionally, ablation experiments validate the effectiveness of each module.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11479380PMC
http://dx.doi.org/10.3390/s24196495DOI Listing

Publication Analysis

Top Keywords

strip steel
20
defect detection
20
steel surface
16
surface defect
16
detection
10
lightweight strip
8
detection network
8
based improved
8
improved yolov8
8
detection accuracy
8

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!