Xuanyu Ge
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xuanyu Ge has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Jie Bai
Beijing Jiaotong University
9 shared publications - Yong Qin
State Key Laboratory of Advanced Rail Autonomous Operation, Beijing Jiaotong University, Beijing 100044, China
9 shared publications - Zhiwei Cao
Beijing Jiaotong University
9 shared publications - Lirong Lian
Beijing Jiaotong University
8 shared publications - Yang Gao
Beijing Jiaotong University
8 shared publications - Hang Yu
Beijing Jiaotong University
6 shared publications
Latest Publications
- Open Access
- 6 June 2026
- Published by Elsevier in Computer-Aided Civil and Infrastructure Engineering
- Vol. 50
An efficient feature aggregation network for urban road damage detection using street-view images
- 6 June 2026
- Published by Elsevier in Computer-Aided Civil and Infrastructure Engineering
- Vol. 50
Open AccessAn efficient feature aggregation network for urban road damage detection using street-view images
- 24 April 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
Real-Time Railway Scene Perception Based on Fast Reconvolution Skip Fusion and Dual Attention Ladder Feature Enhancement
The safety of railway operations is closely related to the state of the train operating environment. Railway scene perception methods can sense the train operating environment and provide technical support for auxiliary driving. However, existing railway scene perception methods require large computations and they are hard to balance between speed and accuracy. There is, therefore, an urgent need to develop a fast and accurate railway scene perception algorithm. To address the need for fast and accurate perception of railway scenes, we propose a real-time railway scene perception network (RRSPNet). Firstly, we develop a lightweight dual-branch backbone and a fast reconvolution skip fusion for rapid extraction of image features. Secondly, we propose a double attention ladder feature enhancement to further improve high-level semantic features and enhance the overall perception accuracy of the network. Finally, we construct two different railway scene data sets: a subway tunnel data set named Metroscapes and a high-speed railway data set named Railscapes. We test the proposed algorithm on both data sets and the public data set rectified linear unit. The results demonstrate its superiority.
- 24 April 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
Real-Time Railway Scene Perception Based on Fast Reconvolution Skip Fusion and Dual Attention Ladder Feature Enhancement
The safety of railway operations is closely related to the state of the train operating environment. Railway scene perception methods can sense the train operating environment and provide technical support for auxiliary driving. However, existing railway scene perception methods require large computations and they are hard to balance between speed and accuracy. There is, therefore, an urgent need to develop a fast and accurate railway scene perception algorithm. To address the need for fast and accurate perception of railway scenes, we propose a real-time railway scene perception network (RRSPNet). Firstly, we develop a lightweight dual-branch backbone and a fast reconvolution skip fusion for rapid extraction of image features. Secondly, we propose a double attention ladder feature enhancement to further improve high-level semantic features and enhance the overall perception accuracy of the network. Finally, we construct two different railway scene data sets: a subway tunnel data set named Metroscapes and a high-speed railway data set named Railscapes. We test the proposed algorithm on both data sets and the public data set rectified linear unit. The results demonstrate its superiority.
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (5) , 4221-4232
RAE3D: Multiscale Aggregation-Enhanced 3D Object Detection for Rail Transit Obstacle Perception
Point cloud-based 3D object detection technology provides precise information for detecting obstacles in front of trains. In rail transit scenarios, obstacles are usually located at a distance, and the sparsity of point cloud data leads to information loss during feature extraction and spatial transformation, adversely affecting the accuracy of obstacle detection. To tackle this issue, we propose RAE3D, a single-stage end-to-end architecture that incorporates a multiscale voxel feature aggregation module on point queries (MVA-PQ) and a bird's-eye view multilevel auxiliary (BEV-MLA) module for efficient 3D object detection. The MVA-PQ module encodes multiscale voxel features into centroids of the final voxel layer, integrating spatial and scale information. The BEV-MLA module converts shallow 3D features into sparse 2D features using height compression, guiding the network to learn the spatial structure of small objects. We also introduce a 3D centroid offset loss for optimizing bounding boxes. Extensive experiments on the Rail3D and KITTI datasets have demonstrated the superiority of the proposed RAE3D.
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (5) , 4221-4232
RAE3D: Multiscale Aggregation-Enhanced 3D Object Detection for Rail Transit Obstacle Perception
Point cloud-based 3D object detection technology provides precise information for detecting obstacles in front of trains. In rail transit scenarios, obstacles are usually located at a distance, and the sparsity of point cloud data leads to information loss during feature extraction and spatial transformation, adversely affecting the accuracy of obstacle detection. To tackle this issue, we propose RAE3D, a single-stage end-to-end architecture that incorporates a multiscale voxel feature aggregation module on point queries (MVA-PQ) and a bird's-eye view multilevel auxiliary (BEV-MLA) module for efficient 3D object detection. The MVA-PQ module encodes multiscale voxel features into centroids of the final voxel layer, integrating spatial and scale information. The BEV-MLA module converts shallow 3D features into sparse 2D features using height compression, guiding the network to learn the spatial structure of small objects. We also introduce a 3D centroid offset loss for optimizing bounding boxes. Extensive experiments on the Rail3D and KITTI datasets have demonstrated the superiority of the proposed RAE3D.
- 23 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Transportation Systems Magazine
- Vol. 17 (2) , 6-22
A Continuous Autonomous Train Positioning Method Using Stereo Vision and Object Tracking
Accurate and reliable train positioning is essential for safe railway operations. However, traditional infrastructure-based methods lack the ability for autonomy and continuous positioning. To solve the problem, we propose a novel modular visual processing framework for continuous train positioning. Environmental information captured by stereo vision sensors is processed using a feature extraction algorithm to detect landmarks along the railway. The detection results are input into a dual-stream parallel processing architecture, where an anchor-based stereo matching module calculates the depth values of detected landmarks, providing essential spatial information. Simultaneously, a dynamic region of interest-based multiobject tracking module assigns unique identification codes to each landmark, facilitating the integration of landmark detection results with their corresponding depth values. This correlation allows for the tracking of changes in landmark positions and the calculation of displacement caused by train motion, leading to a more accurate estimation of the train's location. Subsequently, the train mileage is matched against a database track map to obtain the final precise position. Field tests on Beijing Metro Line 9 and the Capital Airport Line demonstrate an average mean relative error of 0.19% and positioning accuracy within 1 m over a range of 100 m.
- 23 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Transportation Systems Magazine
- Vol. 17 (2) , 6-22
A Continuous Autonomous Train Positioning Method Using Stereo Vision and Object Tracking
Accurate and reliable train positioning is essential for safe railway operations. However, traditional infrastructure-based methods lack the ability for autonomy and continuous positioning. To solve the problem, we propose a novel modular visual processing framework for continuous train positioning. Environmental information captured by stereo vision sensors is processed using a feature extraction algorithm to detect landmarks along the railway. The detection results are input into a dual-stream parallel processing architecture, where an anchor-based stereo matching module calculates the depth values of detected landmarks, providing essential spatial information. Simultaneously, a dynamic region of interest-based multiobject tracking module assigns unique identification codes to each landmark, facilitating the integration of landmark detection results with their corresponding depth values. This correlation allows for the tracking of changes in landmark positions and the calculation of displacement caused by train motion, leading to a more accurate estimation of the train's location. Subsequently, the train mileage is matched against a database track map to obtain the final precise position. Field tests on Beijing Metro Line 9 and the Capital Airport Line demonstrate an average mean relative error of 0.19% and positioning accuracy within 1 m over a range of 100 m.
- 21 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-15
An Anomaly Detection Method for Railway Track Using Semisupervised Learning and Vision-Lidar Decision Fusion
Anomaly detection of the railway track is essential to protect the safety of railway transportation. However, the railway track is often disturbed by unknown anomalies, making it challenging to detect anomalies using only supervised learning and visual sensors. To address these problems, this paper proposes a railway track anomaly detection method using semi-supervised learning and vision-lidar decision fusion. The method consists of three parts: supervised pre-detection, semi-supervised re-detection, and decision-level fusion. In the pre-detection stage, an enhanced instance segmentation algorithm is used to predetect known and unknown anomalies to improve the overall performance. In the re-detection stage, the reconstruction method, semi-supervised learning, and structured light point cloud are combined to re-detect anomalies, especially unknown anomalies. In the fusion stage, the fusion of pre-detection and redetection at the decision level further advances the accuracy and credibility of anomaly detection. Experimental results show that the proposed method achieves a mean average precision (mAP 0.50:0.95) of 92.2% and a mean average recall (mAR 0.50:0.95) of 94.5%. The proposed method is superior to the single vision-based or point cloud-based methods in anomaly detection. In addition, the proposed method provides a general solution to anomaly detection and extends the application of structured light point cloud.
- 21 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-15
An Anomaly Detection Method for Railway Track Using Semisupervised Learning and Vision-Lidar Decision Fusion
Anomaly detection of the railway track is essential to protect the safety of railway transportation. However, the railway track is often disturbed by unknown anomalies, making it challenging to detect anomalies using only supervised learning and visual sensors. To address these problems, this paper proposes a railway track anomaly detection method using semi-supervised learning and vision-lidar decision fusion. The method consists of three parts: supervised pre-detection, semi-supervised re-detection, and decision-level fusion. In the pre-detection stage, an enhanced instance segmentation algorithm is used to predetect known and unknown anomalies to improve the overall performance. In the re-detection stage, the reconstruction method, semi-supervised learning, and structured light point cloud are combined to re-detect anomalies, especially unknown anomalies. In the fusion stage, the fusion of pre-detection and redetection at the decision level further advances the accuracy and credibility of anomaly detection. Experimental results show that the proposed method achieves a mean average precision (mAP 0.50:0.95) of 92.2% and a mean average recall (mAR 0.50:0.95) of 94.5%. The proposed method is superior to the single vision-based or point cloud-based methods in anomaly detection. In addition, the proposed method provides a general solution to anomaly detection and extends the application of structured light point cloud.
- 4 January 2024
- Published by Springer Nature
- p. 37-44
A Fine-Grained Method for Detecting Defects of Track Fasteners Using RGB-D Image
- 4 January 2024
- Published by Springer Nature
- p. 37-44
A Fine-Grained Method for Detecting Defects of Track Fasteners Using RGB-D Image
- 4 January 2024
- Published by Springer Nature
- p. 128-134
A Foreign Object Detection Method for Railway Overhead Lines Based on Few-Shot Learning
- 4 January 2024
- Published by Springer Nature
- p. 128-134
A Foreign Object Detection Method for Railway Overhead Lines Based on Few-Shot Learning
- 4 January 2024
- Published by Springer Nature
- p. 63-72
A Lightweight Pedestrian Intrusion Detection Algorithm Based on On-Board Video
- 4 January 2024
- Published by Springer Nature
- p. 63-72
A Lightweight Pedestrian Intrusion Detection Algorithm Based on On-Board Video
- 4 January 2024
- Published by Springer Nature
- p. 73-81
A Railway Similarity Multiple Object Tracking Framework Based on Vehicle Front Video
- 4 January 2024
- Published by Springer Nature
- p. 73-81
A Railway Similarity Multiple Object Tracking Framework Based on Vehicle Front Video