Yanfu Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yanfu Li has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Hongli Liu
College of Electrical and Information Engineering, Hunan University, Changsha, China
6 shared publications - Liang Chen
State Key Laboratory of Industrial Control Technology, Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China
3 shared publications Xiaoyun Zhong
College of Electrical and Information Engineering, Hunan University, Changsha 410082, China
2 shared publications- Ziji Ma
College of Electrical and Information Engineering, Hunan University, Changsha 410082, China
2 shared publications - Bo Shi
College of Electrical and Information Engineering, Hunan University, Changsha, China
1 shared publication - Chao Chen
State Key Laboratory of Transient Optics and Photonics, Xian Institute of Optics and Precision Mechanics, Chinese Academy of Sciences (CAS), Xian, China
1 shared publication
Latest Publications
- 29 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
Region and Edge-Aware Network for Rail Surface Defect Segmentation
Rail surface defect segmentation can provide a reliable basis for the severity evaluation of rail diseases. The deep learning technology has been widely applied to segment rail surface defects due to the powerful feature representation ability. However, most of the existing deep learning-based methods often produce inaccurate defect region boundaries and unsatisfactory segmentation results since the inadequate integration of contextual information and insufficient edge features. To tackle this problem, a novel region and edge-aware network (REA-Net) is proposed for rail surface defect segmentation in this paper. REA-Net adopts an encoder-decoder framework, where the encoder network incorporates three modules: feature pyramid edge module, multi-task learning module, and cross-level fusion module, to encode richer context information and finer-grained features at each stage. The decoder network aggregates the encoding features from each stage to obtain decoding features, and final these features are used to predict the defect segmentation results. Extensive experiments are conducted on expanded public rail surface defect dataset (RSDD) and the results demonstrate our proposed REA-Net achieves good segmentation performance and outperforms the state-of-the-arts in terms of F 1 -scores and IoU.
- 29 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
Region and Edge-Aware Network for Rail Surface Defect Segmentation
Rail surface defect segmentation can provide a reliable basis for the severity evaluation of rail diseases. The deep learning technology has been widely applied to segment rail surface defects due to the powerful feature representation ability. However, most of the existing deep learning-based methods often produce inaccurate defect region boundaries and unsatisfactory segmentation results since the inadequate integration of contextual information and insufficient edge features. To tackle this problem, a novel region and edge-aware network (REA-Net) is proposed for rail surface defect segmentation in this paper. REA-Net adopts an encoder-decoder framework, where the encoder network incorporates three modules: feature pyramid edge module, multi-task learning module, and cross-level fusion module, to encode richer context information and finer-grained features at each stage. The decoder network aggregates the encoding features from each stage to obtain decoding features, and final these features are used to predict the defect segmentation results. Extensive experiments are conducted on expanded public rail surface defect dataset (RSDD) and the results demonstrate our proposed REA-Net achieves good segmentation performance and outperforms the state-of-the-arts in terms of F 1 -scores and IoU.
- Open Access
- 1 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Journal
- Vol. 16 (3) , 1-11
Stress-Induced Polarization-Maintaining Large-Mode-Area Photonic Crystal Fibers With Deviation of the Single-Mode Transmission Band and Delocalization of Higher-Order Modes
The nonlinear effects and laser-induced optical and thermal damage in optical fibers, together with the limitations of beam quality and mode-field area, restrict the power scaling-up of single-mode output for developing high-power fiber lasers in the kilowatt and above range. The design of photonic crystal fibers (PCFs) with large mode areas is an effective way to address this problem. In this paper, the demands and challenges of designing very large-mode-area (VLMA-) PCFs are discussed, including the overall fiber structure design and property simulation, especially the precise definition of single-mode operating conditions of VLMA-PCFs. Finally, an advanced stress-induced polarization-maintaining, Yb-doped, PCF structure with a large mode area realized by introducing both leakage channels and higher order mode-filtering units is proposed and analyzed theoretically, for which a maximum core diameter of 101 $\boldsymbol{\mu}{\text{m}}$ and single-mode field diameter of 76.33 $\boldsymbol{\mu}{\text{m}}$ at 1064 $\text{nm}$ and a birefringence value $\boldsymbol{> 10^{-4}}$ orders of magnitude are achieved.
- 1 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Journal
- Vol. 16 (3) , 1-11
Open AccessStress-Induced Polarization-Maintaining Large-Mode-Area Photonic Crystal Fibers With Deviation of the Single-Mode Transmission Band and Delocalization of Higher-Order Modes
The nonlinear effects and laser-induced optical and thermal damage in optical fibers, together with the limitations of beam quality and mode-field area, restrict the power scaling-up of single-mode output for developing high-power fiber lasers in the kilowatt and above range. The design of photonic crystal fibers (PCFs) with large mode areas is an effective way to address this problem. In this paper, the demands and challenges of designing very large-mode-area (VLMA-) PCFs are discussed, including the overall fiber structure design and property simulation, especially the precise definition of single-mode operating conditions of VLMA-PCFs. Finally, an advanced stress-induced polarization-maintaining, Yb-doped, PCF structure with a large mode area realized by introducing both leakage channels and higher order mode-filtering units is proposed and analyzed theoretically, for which a maximum core diameter of 101 $\boldsymbol{\mu}{\text{m}}$ and single-mode field diameter of 76.33 $\boldsymbol{\mu}{\text{m}}$ at 1064 $\text{nm}$ and a birefringence value $\boldsymbol{> 10^{-4}}$ orders of magnitude are achieved.
- 3 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (11) , 20098-20109
Robust Registration of Rail Profile and Complete Detection of Outliers in Complex Field Environment
The accurate measurement of rail wear is critical in track quality inspection. Usually, by matching the measured profile with the standard one based on the unworn rail waist double circle segment (DCS), and comparing their railhead differences, we obtain the rail wear. However, in the complex field environment, this task becomes tricky. For profile registration, one is that the location of rail waist becomes difficult with lots of outliers mixed in the profile, and the other is that the obtained rail waist could be polluted or incomplete. For wear measurement, the outliers scattered on the railhead could cause serious errors. This paper is devoted to solving the above problems. For problem 1, firstly, the rail waist is located after a preprocessing procedure. Then, utilizing the proposed hybrid model called R-H-ICP, we realize the profile registration with a process from coarse to fine. For problem 2, by using the standard profile and the reconstructed one with wear constraints to serve as the template separately, and computing the distance from each point of railhead on measured profile to the template, both the distinct and the inapparent outliers are detected precisely. The efficiency and superiority of proposed methods were verified by vast experiments. For the former, compared with DCS and ICP, the R-H-ICP not only improves the profile utilization ratio obviously, also guarantees the registration accuracy as far as possible. For the latter, the F1-Measure average score of outlier detection reaches 0.998, which outperforms some classical models markedly.
- 3 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (11) , 20098-20109
Robust Registration of Rail Profile and Complete Detection of Outliers in Complex Field Environment
The accurate measurement of rail wear is critical in track quality inspection. Usually, by matching the measured profile with the standard one based on the unworn rail waist double circle segment (DCS), and comparing their railhead differences, we obtain the rail wear. However, in the complex field environment, this task becomes tricky. For profile registration, one is that the location of rail waist becomes difficult with lots of outliers mixed in the profile, and the other is that the obtained rail waist could be polluted or incomplete. For wear measurement, the outliers scattered on the railhead could cause serious errors. This paper is devoted to solving the above problems. For problem 1, firstly, the rail waist is located after a preprocessing procedure. Then, utilizing the proposed hybrid model called R-H-ICP, we realize the profile registration with a process from coarse to fine. For problem 2, by using the standard profile and the reconstructed one with wear constraints to serve as the template separately, and computing the distance from each point of railhead on measured profile to the template, both the distinct and the inapparent outliers are detected precisely. The efficiency and superiority of proposed methods were verified by vast experiments. For the former, compared with DCS and ICP, the R-H-ICP not only improves the profile utilization ratio obviously, also guarantees the registration accuracy as far as possible. For the latter, the F1-Measure average score of outlier detection reaches 0.998, which outperforms some classical models markedly.
- Open Access
- 26 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 36207-36217
Vision-Based Position Deviation Measurement of Rail Corrugation Chord Measuring Points Under Bi-Linear Laser Assistance
During the dynamic measurement of chord-based rail corrugation, with the interferences of curve rail and train snaking movement, it is hard to ensure that the measuring points on the rail surface can trace the railhead centerline well the whole time. This introduces the position deviations to the measurement system, and leads to the measurement results cannot reflect the true rail irregularity state. To solve the problem, a position deviation measurement method based on the assistance of bi-linear laser is proposed in this paper. First, by means of three verifications composed of color, dimension and position, the laser stripe regions on railhead are located from original image effectively. Then, by suppressing stripe highlight texture and modifying the traditional Steger algorithm with flexible-widths Gaussian template, we extract the laser stripe centerline accurately, and depict the railhead boundary fast. Last, by locating three chord-based measuring points and calculating the distances from them to the railhead centerline, we obtain the position deviations of each point. The efficiency and superiority of proposed method are verified by vast experiments. The results show that the accuracy of the position deviation of the chord-based measuring points is limited within 0.4mm.
- 26 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 36207-36217
Open AccessVision-Based Position Deviation Measurement of Rail Corrugation Chord Measuring Points Under Bi-Linear Laser Assistance
During the dynamic measurement of chord-based rail corrugation, with the interferences of curve rail and train snaking movement, it is hard to ensure that the measuring points on the rail surface can trace the railhead centerline well the whole time. This introduces the position deviations to the measurement system, and leads to the measurement results cannot reflect the true rail irregularity state. To solve the problem, a position deviation measurement method based on the assistance of bi-linear laser is proposed in this paper. First, by means of three verifications composed of color, dimension and position, the laser stripe regions on railhead are located from original image effectively. Then, by suppressing stripe highlight texture and modifying the traditional Steger algorithm with flexible-widths Gaussian template, we extract the laser stripe centerline accurately, and depict the railhead boundary fast. Last, by locating three chord-based measuring points and calculating the distances from them to the railhead centerline, we obtain the position deviations of each point. The efficiency and superiority of proposed method are verified by vast experiments. The results show that the accuracy of the position deviation of the chord-based measuring points is limited within 0.4mm.
- 19 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 21 (3) , 1074-1085
The Outlier and Integrity Detection of Rail Profile Based on Profile Registration
For rail wear measurement, the process of profile registration is critical. Nowadays, the widely used method is the rail waist double circle segment method (DCS). However, this method may be invalid in actual applications because of the influence of the following two factors: one is the outliers mixed into profiles and the other is the profile diversity. The former induces the misalignment between the measured profile and the standard one, and the latter may destroy the integrity of rail waist, which makes that the measured profile cannot be matched with the standard one through DCS. To solve the two problems, a hybrid profile registration method is proposed in this paper. First, by locating new matching primitives to realize coarse registration, we check the profile integrity fast. Then, for complete profile, we rematch its original measured profile with the standard one finely based on DCS to detect and remove the outliers correctly. The efficiency and superiority of the proposed method were verified by numerous experiments. The results show that the average score of F1-Measure for outlier detection reaches 0.95, which outperforms some classical models obviously. Meanwhile, the result of the profile integrity check is also basically coincided with the real face of test zones. Furthermore, the system can run at a speed of 21.95 km/h under our experimental setup, which is far higher than that of the rail maintenance train (up to 5 km/h).
- 19 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 21 (3) , 1074-1085
The Outlier and Integrity Detection of Rail Profile Based on Profile Registration
For rail wear measurement, the process of profile registration is critical. Nowadays, the widely used method is the rail waist double circle segment method (DCS). However, this method may be invalid in actual applications because of the influence of the following two factors: one is the outliers mixed into profiles and the other is the profile diversity. The former induces the misalignment between the measured profile and the standard one, and the latter may destroy the integrity of rail waist, which makes that the measured profile cannot be matched with the standard one through DCS. To solve the two problems, a hybrid profile registration method is proposed in this paper. First, by locating new matching primitives to realize coarse registration, we check the profile integrity fast. Then, for complete profile, we rematch its original measured profile with the standard one finely based on DCS to detect and remove the outliers correctly. The efficiency and superiority of the proposed method were verified by numerous experiments. The results show that the average score of F1-Measure for outlier detection reaches 0.95, which outperforms some classical models obviously. Meanwhile, the result of the profile integrity check is also basically coincided with the real face of test zones. Furthermore, the system can run at a speed of 21.95 km/h under our experimental setup, which is far higher than that of the rail maintenance train (up to 5 km/h).
- 13 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 68 (1) , 250-260
An Automated System for Position Monitoring and Correction of Chord-Based Rail Corrugation Measuring Points
Rail corrugation impacts the riding quality and safety of railway systems. The chord-based method is one of the common methods for rail corrugation dynamic measurement. However, during the process of continuous operation, it is hard to ensure that the measuring points on the rail surface can trace the railhead centerline well the whole time. This introduces the position deviations to the system, and leads to the measurement results not reflecting the true rail irregularity state. To solve the problem, an automated system for position monitoring and correction of chord-based measuring points is constructed in this paper. The proposed system comprises the position monitoring subsystem (PMS) and the position correction subsystem (PCS). The PMS monitors the positions of measuring points with given sampling interval, and calculates the position deviations with respect to the railhead centerline. Once the deviation exceeds the preset range, the PCS makes corresponding operations to pull the measuring points back to the effective range. Extensive experiments show that the error of PMS is limited within 0.6 mm, and the PCS can correct the position deviations in a timely manner according to the correction criteria. Furthermore, with 20-cm image sampling interval, our system can run at 6 km/h under our experimental setup, which is higher than that of rail maintenance trains (up to 5 km/h).
- 13 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 68 (1) , 250-260
An Automated System for Position Monitoring and Correction of Chord-Based Rail Corrugation Measuring Points
Rail corrugation impacts the riding quality and safety of railway systems. The chord-based method is one of the common methods for rail corrugation dynamic measurement. However, during the process of continuous operation, it is hard to ensure that the measuring points on the rail surface can trace the railhead centerline well the whole time. This introduces the position deviations to the system, and leads to the measurement results not reflecting the true rail irregularity state. To solve the problem, an automated system for position monitoring and correction of chord-based measuring points is constructed in this paper. The proposed system comprises the position monitoring subsystem (PMS) and the position correction subsystem (PCS). The PMS monitors the positions of measuring points with given sampling interval, and calculates the position deviations with respect to the railhead centerline. Once the deviation exceeds the preset range, the PCS makes corresponding operations to pull the measuring points back to the effective range. Extensive experiments show that the error of PMS is limited within 0.6 mm, and the PCS can correct the position deviations in a timely manner according to the correction criteria. Furthermore, with 20-cm image sampling interval, our system can run at 6 km/h under our experimental setup, which is higher than that of rail maintenance trains (up to 5 km/h).
- 30 March 2018
- Published by Springer Nature
- p. 37-45
Profile Calibration of Dynamically Measuring Rail Wear Using LIS
- 30 March 2018
- Published by Springer Nature
- p. 37-45
Profile Calibration of Dynamically Measuring Rail Wear Using LIS