Yunpeng Wu
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
Yunpeng Wu has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
Yong Qin
5 shared publications- Fengxiang Guo
Kunming University of Science and Technology
4 shared publications Tong Yang
4 shared publicationsChanghong Shao
3 shared publications- Yong Qin
State Key Laboratory of Advanced Rail Autonomous Operation, Beijing Jiaotong University, Beijing 100044, China
3 shared publications Hao Zhang
School of Safety Engineering and Emergency Management, Shijiazhuang Tiedao University, Shijiazhuang, China
2 shared publications
Latest Publications
- 19 November 2025
- Published by Elsevier in Measurement
- Vol. 259
An anchor-free automatic evaluation system for pavement surface distress using UAV aerial photograph
- 19 November 2025
- Published by Elsevier in Measurement
- Vol. 259
An anchor-free automatic evaluation system for pavement surface distress using UAV aerial photograph
- 4 August 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (8) , 085007
An anchor-free selective state space framework for real-time tunnel structure health monitoring
Regular tunnel inspections are essential for ensuring structural safety, yet current convolutional neural networks - or Transformer-based approaches struggle to balance accuracy, speed, and adaptability to complex tunnel environments. This study proposes an anchor-free selective state space (AFS3) framework specifically designed for real-time tunnel structure health monitoring. First, an anchor-free detection mechanism that directly regresses object boundaries from center points, enabling flexible handling of multi-scale and irregularly distributed defects. Second, a residual mamba module-based backbone that integrates selective state space modeling with residual learning to enhance long-range dependency modeling and fine-grained feature extraction while maintaining low computational cost. Besides, a novel C3OK2 neck incorporating omni-dimensional dynamic convolution, which dynamically adjusts kernel weights across all dimensions to improve multi-scale feature fusion under complex tunnel conditions. Finally, extensive experiments on a custom-labeled multi-device tunnel defect dataset demonstrate that AFS3 outperforms the latest YOLO11 and other surpasses existing state-of-the-art models in both accuracy and inference speed, showing strong potential for mobile deployment. To foster further research, the tunnel structure image dataset can be accessed at https://github.com/Kzz1yt/Tunnel_structure_image_data.
- 4 August 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (8) , 085007
An anchor-free selective state space framework for real-time tunnel structure health monitoring
Regular tunnel inspections are essential for ensuring structural safety, yet current convolutional neural networks - or Transformer-based approaches struggle to balance accuracy, speed, and adaptability to complex tunnel environments. This study proposes an anchor-free selective state space (AFS3) framework specifically designed for real-time tunnel structure health monitoring. First, an anchor-free detection mechanism that directly regresses object boundaries from center points, enabling flexible handling of multi-scale and irregularly distributed defects. Second, a residual mamba module-based backbone that integrates selective state space modeling with residual learning to enhance long-range dependency modeling and fine-grained feature extraction while maintaining low computational cost. Besides, a novel C3OK2 neck incorporating omni-dimensional dynamic convolution, which dynamically adjusts kernel weights across all dimensions to improve multi-scale feature fusion under complex tunnel conditions. Finally, extensive experiments on a custom-labeled multi-device tunnel defect dataset demonstrate that AFS3 outperforms the latest YOLO11 and other surpasses existing state-of-the-art models in both accuracy and inference speed, showing strong potential for mobile deployment. To foster further research, the tunnel structure image dataset can be accessed at https://github.com/Kzz1yt/Tunnel_structure_image_data.
- Open Access
- 12 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-19
A crack detection and quantification method using matched filter and photograph reconstruction
Crack detection is a critical task for bridge maintenance and management. While popular deep learning algorithms have shown promise, their reliance on large, high-quality training datasets, which are often unavailable in engineering practice, limits their applicability. By contrast, traditional digital image processing methods offer low computational costs and strong interpretability, making continued research in this area highly valuable. This study proposes an automatic crack detection and quantification approach based on digital image processing combined with unmanned aerial vehicle (UAV) flight parameters. First, the characteristics of the bridge images collected by the UAVs were thoroughly analyzed. An enhanced matched-filter algorithm was designed to achieve crack segmentation. Morphological methods were employed to extract the skeletons of the segmented cracks, enabling the calculation of actual crack lengths. Finally, a 3D model was constructed by integrating the detection results with the image-shooting parameters. This 3D model, annotated with detected cracks, provides an intuitive and comprehensive representation of bridge damage, facilitating informed decision making in maintenance planning and resource allocation. To verify the accuracy of the enhanced matched filter algorithm, it was compared with other digital image processing methods on public datasets, achieving average results of 97.9% for Pixel Accuracy (PA), 72.5% for the F1-score, and 58.1% for Intersection over Union (Iou) across three typical sub-datasets. Moreover, the proposed methodologies were successfully applied to an arch bridge with an error of only 2%, thereby demonstrating their applicability to real-world scenarios.
- 12 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-19
Open AccessA crack detection and quantification method using matched filter and photograph reconstruction
Crack detection is a critical task for bridge maintenance and management. While popular deep learning algorithms have shown promise, their reliance on large, high-quality training datasets, which are often unavailable in engineering practice, limits their applicability. By contrast, traditional digital image processing methods offer low computational costs and strong interpretability, making continued research in this area highly valuable. This study proposes an automatic crack detection and quantification approach based on digital image processing combined with unmanned aerial vehicle (UAV) flight parameters. First, the characteristics of the bridge images collected by the UAVs were thoroughly analyzed. An enhanced matched-filter algorithm was designed to achieve crack segmentation. Morphological methods were employed to extract the skeletons of the segmented cracks, enabling the calculation of actual crack lengths. Finally, a 3D model was constructed by integrating the detection results with the image-shooting parameters. This 3D model, annotated with detected cracks, provides an intuitive and comprehensive representation of bridge damage, facilitating informed decision making in maintenance planning and resource allocation. To verify the accuracy of the enhanced matched filter algorithm, it was compared with other digital image processing methods on public datasets, achieving average results of 97.9% for Pixel Accuracy (PA), 72.5% for the F1-score, and 58.1% for Intersection over Union (Iou) across three typical sub-datasets. Moreover, the proposed methodologies were successfully applied to an arch bridge with an error of only 2%, thereby demonstrating their applicability to real-world scenarios.
- Open Access
- 16 April 2025
- Published by Springer Nature in Research Square
A Crack detection and Quantification Method Using Match Filter and Photograph Reconstruction
Crack detection is a critical task for bridge maintenance and management. While popular deep learning algorithms have shown promise, their reliance on large, high-quality training datasets, which are often unavailable in engineering practice, limits their applicability. By contrast, traditional digital image processing methods offer low computational costs and strong interpretability, making continued research in this area highly valuable. This study proposes an automatic crack detection and quantification approach based on digital image processing combined with unmanned aerial vehicle (UAV) flight parameters. First, the characteristics of the bridge images collected by the UAVs were thoroughly analyzed. An enhanced match-filter algorithm was designed to achieve crack segmentation. Morphological methods were employed to extract the skeletons of the segmented cracks, enabling the calculation of actual crack lengths. Finally, a 3D model was constructed by integrating the detection results with the image-shooting parameters. This 3D model, annotated with detected cracks, provides an intuitive and comprehensive representation of bridge damage, facilitating informed decision making in maintenance planning and resource allocation. To verify the accuracy of the enhanced match filter algorithm, it was compared with other digital image processing methods on public datasets, achieving average results of 97.9% for Pixel Accuracy (PA), 72.5% for the F1-score, and 58.1% for Intersection over Union (Iou) across three typical sub-datasets. Moreover, the proposed methodologies were successfully applied to an arch bridge with an error of only 2%, thereby demonstrating their applicability to real-world scenarios.
- 16 April 2025
- Published by Springer Nature in Research Square
Open AccessA Crack detection and Quantification Method Using Match Filter and Photograph Reconstruction
Crack detection is a critical task for bridge maintenance and management. While popular deep learning algorithms have shown promise, their reliance on large, high-quality training datasets, which are often unavailable in engineering practice, limits their applicability. By contrast, traditional digital image processing methods offer low computational costs and strong interpretability, making continued research in this area highly valuable. This study proposes an automatic crack detection and quantification approach based on digital image processing combined with unmanned aerial vehicle (UAV) flight parameters. First, the characteristics of the bridge images collected by the UAVs were thoroughly analyzed. An enhanced match-filter algorithm was designed to achieve crack segmentation. Morphological methods were employed to extract the skeletons of the segmented cracks, enabling the calculation of actual crack lengths. Finally, a 3D model was constructed by integrating the detection results with the image-shooting parameters. This 3D model, annotated with detected cracks, provides an intuitive and comprehensive representation of bridge damage, facilitating informed decision making in maintenance planning and resource allocation. To verify the accuracy of the enhanced match filter algorithm, it was compared with other digital image processing methods on public datasets, achieving average results of 97.9% for Pixel Accuracy (PA), 72.5% for the F1-score, and 58.1% for Intersection over Union (Iou) across three typical sub-datasets. Moreover, the proposed methodologies were successfully applied to an arch bridge with an error of only 2%, thereby demonstrating their applicability to real-world scenarios.
- Open Access
- 1 January 2025
- Published by Tech Science Press in Structural Durability & Health Monitoring
- Vol. 19 (6) , 1457-1472
Automatic Potential Safety Hazard Detection for High-Speed Railroad Surrounding Environment Using Lightweight Hybrid Dual Tasks Architecture
Utilizing unmanned aerial vehicle (UAV) photography to timely detect and evaluate potential safety hazards (PSHs) around high-speed rail has great potential to complement and reform the existing manual inspections by providing better overhead views and mitigating safety issues. However, UAV inspections based on manual interpretation, which heavily rely on the experience, attention, and judgment of human inspectors, still inevitably suffer from subjectivity and inaccuracy. To address this issue, this study proposes a lightweight hybrid learning algorithm named HDTA (hybrid dual tasks architecture) to automatically and efficiently detect the PSHs of UAV imagery. First, this HDTA architecture seamlessly integrates both detection and segmentation branches within a unified framework. This design enables the model to simultaneously perform PSH detection and railroad parsing, thereby providing comprehensive scene understanding. Such joint learning also lays the foundation for PSH assessment tasks. Second, an innovative lightweight backbone based on the shuffle selective state space model (S4M) is incorporated into HDTA. The state space model approach allows for global contextual information extraction while maintaining linear computational complexity. Furthermore, the incorporation of shuffle operation facilitates more efficient information flow across feature dimensions, enhancing both feature representation and fusion capabilities. Finally, extensive experiments conducted on a railroad environment dataset constructed from UAV imagery demonstrate that the proposed method achieves high detection accuracy while maintaining efficiency and practicality.
- 1 January 2025
- Published by Tech Science Press in Structural Durability & Health Monitoring
- Vol. 19 (6) , 1457-1472
Open AccessAutomatic Potential Safety Hazard Detection for High-Speed Railroad Surrounding Environment Using Lightweight Hybrid Dual Tasks Architecture
Utilizing unmanned aerial vehicle (UAV) photography to timely detect and evaluate potential safety hazards (PSHs) around high-speed rail has great potential to complement and reform the existing manual inspections by providing better overhead views and mitigating safety issues. However, UAV inspections based on manual interpretation, which heavily rely on the experience, attention, and judgment of human inspectors, still inevitably suffer from subjectivity and inaccuracy. To address this issue, this study proposes a lightweight hybrid learning algorithm named HDTA (hybrid dual tasks architecture) to automatically and efficiently detect the PSHs of UAV imagery. First, this HDTA architecture seamlessly integrates both detection and segmentation branches within a unified framework. This design enables the model to simultaneously perform PSH detection and railroad parsing, thereby providing comprehensive scene understanding. Such joint learning also lays the foundation for PSH assessment tasks. Second, an innovative lightweight backbone based on the shuffle selective state space model (S4M) is incorporated into HDTA. The state space model approach allows for global contextual information extraction while maintaining linear computational complexity. Furthermore, the incorporation of shuffle operation facilitates more efficient information flow across feature dimensions, enhancing both feature representation and fusion capabilities. Finally, extensive experiments conducted on a railroad environment dataset constructed from UAV imagery demonstrate that the proposed method achieves high detection accuracy while maintaining efficiency and practicality.
- 27 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (1) , 1071-1087
Automatic Potential Safety Hazard Evaluation System for Environment Around High-Speed Railroad Using Hybrid U-Shape Learning Architecture
Potential safety hazards (PSHs) around the high-speed railroad need to be detected and evaluated regularly and timely to ensure high-speed railroad operation safety. Unmanned aerial vehicle (UAV)-based PSH evaluation has great potential to supplement the current manual visual inspection tasks by providing better overhead views and less man-made accidents. This study presents an evaluation system for PSHs along high-speed railroad tracks. First, a novel hybrid learning architecture named UYOLO (U-shape You Only Look Once) is designed, which integrate the CSP-based backbone and detection branch to produce three scale high-level features for the object detection. Then, an innovative parsing branch inserted behind high-level layer of the structure progressively transmits context information to the shallow layer to accurately accomplish the pixel-level parsing task. Second, a new loss function using minimum point distance IoU (MPD-IoU) is designed and incorporated into the architecture to optimize the coordinate regression process of the predicted bounding boxes. Conveniently, an image-based hazard evaluation model is also developed and integrated to rate the hazard level of the detected PSHs. Finally, extensive experiments conducted on the track environment dataset established with UAV imagery indicate the proposed system can achieve a high detection rate yet remains efficient and convenient.
- 27 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (1) , 1071-1087
Automatic Potential Safety Hazard Evaluation System for Environment Around High-Speed Railroad Using Hybrid U-Shape Learning Architecture
Potential safety hazards (PSHs) around the high-speed railroad need to be detected and evaluated regularly and timely to ensure high-speed railroad operation safety. Unmanned aerial vehicle (UAV)-based PSH evaluation has great potential to supplement the current manual visual inspection tasks by providing better overhead views and less man-made accidents. This study presents an evaluation system for PSHs along high-speed railroad tracks. First, a novel hybrid learning architecture named UYOLO (U-shape You Only Look Once) is designed, which integrate the CSP-based backbone and detection branch to produce three scale high-level features for the object detection. Then, an innovative parsing branch inserted behind high-level layer of the structure progressively transmits context information to the shallow layer to accurately accomplish the pixel-level parsing task. Second, a new loss function using minimum point distance IoU (MPD-IoU) is designed and incorporated into the architecture to optimize the coordinate regression process of the predicted bounding boxes. Conveniently, an image-based hazard evaluation model is also developed and integrated to rate the hazard level of the detected PSHs. Finally, extensive experiments conducted on the track environment dataset established with UAV imagery indicate the proposed system can achieve a high detection rate yet remains efficient and convenient.
- 12 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (21) , 35997-36010
GPR Imagery-Based Internal Defect Evaluation System for Railroad Tunnel Lining Using Real-Time Instance Segmentation
Railroad tunnel linings may have voids filled with water or air, or areas that lack compaction due to construction processes. These structural defects are hard to detect and require regular inspections to ensure safety. Existing CNN-based inspection systems that employ ground penetrating radar (GPR) imagery sometimes cannot fully assess the defects and ensure the structural integrity of the linings. This study develops an internal defect evaluation system based on an innovative computer vision architecture named YolaTC (You Only Look at Tunnel Coefficients) for monitoring railroad tunnel linings. First, YolaTC is equipped with a novel backbone that has multiple receptive fields available to strengthen multi-granularity feature representation and enrich semantic information in the feature space. Then, a new strip pooling module is developed and incorporated to model long-range context dependencies, improving the segmentation of long but narrow defect regions. Second, the system integrates a novel skeleton extraction-based Deterioration Level Evaluation (DLE) method that can calculate the actual defect length to quantify the level of void degradation. Finally, extensive comparative experiments conducted on a customized dataset established with GPR imagery demonstrate that the proposed system can effectively convert GPR images into valuable information with high accuracy, rapid processing speed, and good adaptation capability in complex tunnel structures.
- 12 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (21) , 35997-36010
GPR Imagery-Based Internal Defect Evaluation System for Railroad Tunnel Lining Using Real-Time Instance Segmentation
Railroad tunnel linings may have voids filled with water or air, or areas that lack compaction due to construction processes. These structural defects are hard to detect and require regular inspections to ensure safety. Existing CNN-based inspection systems that employ ground penetrating radar (GPR) imagery sometimes cannot fully assess the defects and ensure the structural integrity of the linings. This study develops an internal defect evaluation system based on an innovative computer vision architecture named YolaTC (You Only Look at Tunnel Coefficients) for monitoring railroad tunnel linings. First, YolaTC is equipped with a novel backbone that has multiple receptive fields available to strengthen multi-granularity feature representation and enrich semantic information in the feature space. Then, a new strip pooling module is developed and incorporated to model long-range context dependencies, improving the segmentation of long but narrow defect regions. Second, the system integrates a novel skeleton extraction-based Deterioration Level Evaluation (DLE) method that can calculate the actual defect length to quantify the level of void degradation. Finally, extensive comparative experiments conducted on a customized dataset established with GPR imagery demonstrate that the proposed system can effectively convert GPR images into valuable information with high accuracy, rapid processing speed, and good adaptation capability in complex tunnel structures.
- 12 August 2024
- Published by Elsevier in Measurement
- Vol. 239
Hybrid learning architecture for high-speed railroad scene parsing and potential safety hazard evaluation of UAV images
- 12 August 2024
- Published by Elsevier in Measurement
- Vol. 239
Hybrid learning architecture for high-speed railroad scene parsing and potential safety hazard evaluation of UAV images
- 22 May 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (8) , 086206
UAV imagery-based railroad station building inspection using hybrid learning architecture
The apparent defects of railroad station building such as the broken glass, missing screw, and rust corrosion need to be inspected regularly and timely to ensure the safety of passenger. Unmanned aerial vehicle (UAV) imagery-based inspections have the potential to revolutionize current manual visual inspections by providing a better overhead view and mitigating safety concerns. This paper proposes a hybrid learning architecture called YOLOS (you only look once station scene) to simultaneously detect and segment station building surface defects of UAV images. First, a novel squeeze-and-excitation (SE) attention block is integrated into the detection branch to adaptively learn the weights of the feature channels, thereby promoting the network to pay attention to the critical deep features of the objects. And then, a new semantic segmentation branch parallel to the detection branch is designed and assembled in YOLOS for pixel-level defect recognition. Finally, extensive experiments on railroad station dataset established with drone imagery prove the effectiveness and robustness of the SE-based network on station surface defect detection. This method can quickly convert UAV imagery into useful information with a high detection rate.
- 22 May 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (8) , 086206
UAV imagery-based railroad station building inspection using hybrid learning architecture
The apparent defects of railroad station building such as the broken glass, missing screw, and rust corrosion need to be inspected regularly and timely to ensure the safety of passenger. Unmanned aerial vehicle (UAV) imagery-based inspections have the potential to revolutionize current manual visual inspections by providing a better overhead view and mitigating safety concerns. This paper proposes a hybrid learning architecture called YOLOS (you only look once station scene) to simultaneously detect and segment station building surface defects of UAV images. First, a novel squeeze-and-excitation (SE) attention block is integrated into the detection branch to adaptively learn the weights of the feature channels, thereby promoting the network to pay attention to the critical deep features of the objects. And then, a new semantic segmentation branch parallel to the detection branch is designed and assembled in YOLOS for pixel-level defect recognition. Finally, extensive experiments on railroad station dataset established with drone imagery prove the effectiveness and robustness of the SE-based network on station surface defect detection. This method can quickly convert UAV imagery into useful information with a high detection rate.