Results 191 to 200 of about 5,176,577 (228)

Shape-Consistent One-Shot Unsupervised Domain Adaptation for Rail Surface Defect Segmentation

IEEE Transactions on Industrial Informatics, 2023
Deep neural networks have greatly improved the performance of rail surface defect segmentation when the test samples have the same distribution as the training samples.
Shuai Ma, Ke-Chen Song, Menghui Niu, Hongkun Tian, Yanyan Wang, Yunhui Yan   +5 more
semanticscholar   +1 more source

PFCNet: Enhancing Rail Surface Defect Detection With Pixel-Aware Frequency Conversion Networks

IEEE Signal Processing Letters
Applying computer vision techniques to rail surface defect detection (RSDD) is crucial for preventing catastrophic accidents. However, challenges such as complex backgrounds and irregular defect shapes persist. Previous methods have focused on extracting
Yue Wu, Fangfang Qiang, Wu-Jie Zhou, Wei-Qing Yan   +3 more
semanticscholar   +1 more source

RGB-D Rail Surface Defect Inspection Driven by Conditional Diffusion Architecture and Frequency Knowledge

IEEE Sensors Journal
RGB-D rail surface defect inspection (RSDI) is a critical measure for ensuring transportation safety. It improves inspection accuracy by using depth maps, but the issue of poor-quality depth maps in rail defect datasets is often overlooked. Additionally,
Zhi-Hao He, Gong-Yang Li, Zhi Liu
semanticscholar   +1 more source

An image-level weakly supervised segmentation method for No-service rail surface defect with size prior

Mechanical Systems and Signal Processing, 2022
Jing Xu, Yunhui Yan, Defu Zhang
exaly   +2 more sources

RMSDNet: A Lightweight Object Detection Network for Rail Surface Defect

IEEE Transactions on Instrumentation and Measurement
The surface condition of rails is important for ensuring the safe and stable operation of railway vehicles, so real-time defect detection of rail surfaces is essential.
Yuejian Chen, Yan Li, Zaoshi Ying, Zhipeng Wang, Mingjiang Xie   +4 more
semanticscholar   +1 more source

DiffRSD: Diffusion-Based and Integrity-Aware RGB-D Rail Surface Defect Inspection

IEEE transactions on intelligent transportation systems (Print)
Rail quality evaluation ensures the safety of railway transportation, where rail surface defect inspection is one of important tasks. Traditional methods adopt encoder-decoder framework, which is difficult to extract discriminative defect features to ...
Zhengyi Liu, Jun Zhou, Rui Huang, Xianyong Fang, Zhengzheng Tu, Linbo Wang   +5 more
semanticscholar   +1 more source

CSANet: Contour and Semantic Feature Alignment Fusion Network for Rail Surface Defect Detection

IEEE Signal Processing Letters, 2023
Rail surface defect detection for traffic safety has received considerable attention. With the development of deep learning, numerous methods for combining RGB and depth information have been proposed.
Jinxin Yang, Wu-Jie Zhou, Rui-Ming Wu, Meixin Fang   +3 more
semanticscholar   +1 more source

Ordered Cross-Scale Interaction Network for No-Service Rail Surface Defect Segmentation

IEEE Transactions on Instrumentation and Measurement
No-service rail surface defect (NRSD) segmentation plays a key role in industrial intelligent manufacturing to achieve pixel-level defect localization and ensure the quality of rails.
Gong-Yang Li, Xiaofei Zhou, Hongyun Li
semanticscholar   +1 more source

A lightweight rail surface defect detection algorithm integrating multi-attention mechanism and content-aware reassembly of features

Measurement science and technology
Rail surface defect inspection and maintenance play a crucial role in ensuring the safety of railway operations. While existing deep learning-based lightweight detection methods have enhanced the efficiency of manual inspections, their performance ...
Hongzhang Ma, Guo Wang, Yaxing Li, Yongzhi Min   +3 more
semanticscholar   +1 more source

Self-attention adversarial variational autoencoders networks for rail surface defect data expansion

Engineering Research Express
The paucity of rail surface defect samples constrains the generalization capabilities of supervised defect detection methodologies. To address this issue, the Self-Attention Adversarial Variational Autoencoder (SAVAE) is introduced for the purposes of ...
Hua Fu, Fei Kang
semanticscholar   +1 more source