An Improved YOLOv8 Algorithm for Rail Surface Defect Detection

doi:10.1109/ACCESS.2024.3380009

2024-01-01

DOI：10.1109/ACCESS.2024.3380009

原文链接

原文求助

摘要

En 中文

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.

Keyword:

Rail defects detection

deep learning

YOLOv8

convolution module

attention mechanism

loss function

期刊

IEEE Access

IF:

3.6

论文数:

9.8W

被引数:

29.4W

机构

Zhejiang Normal University

学者数:

1.3W

论文数: 8.4K

被引数: 1.2W

引用论文

Personality traits related to juvenile myoclonic epilepsy: MRI reveals prefrontal abnormalities through a voxel-based morphometry study

Epilepsy & Behavior

IF0

2009-06-01

PREAI

Gerardo Maria de Araújo Filho; Andrea Parolin Jackowski; Katia Lin; Mirian S.B. Guaranha; Laura M.F.F. Guilhoto; Henrique Hattori da Silva; Luís Otávio Sales Ferreira Caboclo; Henrique Carrete Júnior; Rodrigo Affonseca Bressan; Elza Márcia T. Yacubian

Effects of low-dose cadmium exposure during gestation and lactation on development and reproduction in rats

Environmental Science and Pollution Research

IF0

2015-03-05

PREAI

Xue Luo; Lianbing Li; Mingfu Ma; Renyan Li

Psychometrics of the Child PTSD Symptom Scale for DSM-5 for Trauma-Exposed Children and Adolescents

Journal of Clinical Child & Adolescent Psychology

IF0

2017-08-18