Browsing by Author "Wang, Yizhong"

Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemOpen Access
    3D reconstruction of rail tracks based on fusion of RGB and infrared sensors
    (IEEE, 2024-08-28) Wang, Yizhong; Kuang, Boyu; Durazo, Isidro; Zhao, Yifan
    Rail tracks, an essential part of the rail system, have remarkably demanded thorough inspections amid rising passenger volumes and high-speed rail development. Non-destructive testing (NDT), without disrupting train operations, aims to mitigate risks by employing safe physical properties like sound, electromagnetic, and light. However, each NDT technique is sensitive to specific damage types, offering limited diagnostic perspectives and placing considerable requirements on operators, resulting in a high cognitive load. To improve the above situation, this study proposes an innovative approach for rail inspection by developing a 3D RGB-T model that combines Visual Testing (VT) and Thermal Inspection (TI) through image registration, 3D reconstruction, sensor fusion, and non-destructive testing (NDT). Their fusion facilities a complementary assessment of rail tracks by capturing both surface texture and thermal radiation to identify damages effectively. The introduction of a novel RGB and IR registration method enables the spatial alignment of images from both, reconstructing the 3D RGB-T model. This model broadens the detection scope beyond the limitations of singular NDT methods, utilizing complementary data to locate and assess the damage extent effectively and accurately. This integrated approach reduces training requirements, minimizes human errors, and provides a clear and interpretable visualization of track conditions.
  • Thumbnail Image
    ItemOpen Access
    Advanced semantic segmentation of aircraft main components based on transfer learning and data-driven approach
    (Springer, 2024-12-31) Thomas, Julien; Kuang, Boyu; Wang, Yizhong; Barnes, Stuart; Jenkins, Karl
    The implementation of Smart Airport and Airport 4.0 visions relies on the integration of automation, artificial intelligence, data science, and aviation technology to enhance passenger experiences and operational efficiency. One essential factor in the integration is the semantic segmentation of the aircraft main components (AMC) perception, which is essential to maintenance, repair, and operations in aircraft and airport operations. However, AMC segmentation has challenges from low data availability, high-quality annotation scarcity, and categorical imbalance, which are common in practical applications, including aviation. This study proposes a novel AMC segmentation solution, employing a transfer learning framework based on a sophisticated DeepLabV3 architecture optimized with a custom-designed Focal Dice Loss function. The proposed solution remarkably suppresses the categorical imbalance challenge and increases the dataset variability with manually annotated images and dynamic augmentation strategies to train a robust AMC segmentation model. The model achieved a notable intersection over union of 84.002% and an accuracy of 91.466%, significantly advancing the AMC segmentation performance. These results demonstrate the effectiveness of the proposed AMC segmentation solution in aircraft and airport operation scenarios. This study provides a pioneering solution to the AMC semantic perception problem and contributes a valuable dataset to the community, which is fundamental to future research on aircraft and airport semantic perception.
  • Thumbnail Image
    ItemOpen Access
    A fiber-guided motorized rotation laser scanning thermography technique for impact damage crack inspection in composites
    (IEEE, 2023-04-11) Liu, Haochen; Tinsley, Lawrence; Deng, Kailun; Wang, Yizhong; Starr, Andrew; Chen, Zhenmao; Zhao, Yifan
    Laser Thermography manifests superior sensitivity and compatibility to detect cracks and small subsurface defects. However, the existing related systems have limitations on either inspection efficiency or unknown directional cracks due to the utilization of stationary heat sources. This article reports a Fiber-guided Motorised Rotation Laser-line Scanning Thermography (FMRLST) system aiming to rapidly inspect cracks of impact damage with unknown direction in composite laminates. An optical head with fibre delivery integrated with a rotation motor is designed and developed to generate novel scanning heating in a circumferential rotation manner. A FEM model is first proposed to simulate the principle of FMRLST testing and produce thermograms for the development of post-processing methods. A damage enhancement method based on Curvelet Transform is developed to enhance the visualization of thermal features of cracks, and purify the resulting image by suppressing the laser-line heating pattern and cancelling noise. The validation on three composite specimens with different levels of impact damage suggests the developed FMRLST system can extract unknown impact surface cracks efficiently. The remarkable sensitivity and flexibility of FMRLST to arbitrary cracks, along with the miniaturized probe-like inspection unit, present its potential in on-site thermographic inspection, and its design is promising to push the LST towards.
  • Thumbnail Image
    ItemOpen Access
    A full 3D reconstruction of rail tracks using a camera array
    (Elsevier, 2023-12-14) Wang, Yizhong; Liu, Haochen; Yang, Lichao; Durazo-Cardenas, Isidro; Namoano, Bernadin; Zhong, Cheng; Zhao, Yifan
    This research addresses limitations found in existing 3D track reconstruction studies, which often focus solely on specific rail sections or encounter deployment challenges with rolling stock. To address this challenge, we propose an innovative solution: a rolling-stock embedded arch camera array scanning system. The system includes a semi-circumferential focusing vision array, an arch camera holder, and a Computer Numerical Control machine to simulate track traverse. We propose an optimal configuration that balances accuracy, full rail coverage, and modelling efficiency. Sensitivity analysis demonstrates a reconstruction accuracy within 0.4 mm when compared to Lidar-generated ground truth models. Two real-world experiments validate the system's effectiveness following essential data preprocessing. This integrated technique, when combined with rail rolling stocks and robotic maintenance platforms, facilitates swift, unmanned, and highly accurate track reconstruction and surveying.