Research Interests
My research interest is in deep learning-based pavement crack detection. In recent years, techniques using Convolutional Neural Networks (CNNs) or Transformers have shown remarkable and promising results. However, detecting pavement cracks in 2D images still poses challenges due to the complex topological structures they exhibit and the influence of various sources of noise. These sources of noise include road surface undulations, tire marks, water stains, oil stains, fallen leaves, and variations in lighting conditions. Therefore, my research aims to focus on developing semi-supervised methods and reducing the data dependency of pavement crack detection models. By exploring semi-supervised techniques, I intend to leverage both labeled and unlabeled data to improve the accuracy and robustness of crack detection models. This approach would allow for more efficient training and alleviate the need for large amounts of labeled data. Ultimately, my goal is to enhance the performance of pavement crack detection systems, enabling more reliable and efficient infrastructure maintenance.
Education
- M.Eng. in Surveying and Mapping, Nanjing University of Information Science and Technology, Sept. 2020 - Jun. 2023
- B.Sc. in Remote Sensing Science and Technology, Nanjing University of Information Science and Technology, Sept. 2016 - Jun. 2020
Publications
- Zhengsen Xu, Xiangda Lei, Haiyan Guan*, 2023. Multi-scale local feature enhanced Transformer network for pavement crack detection. Journal of Image and Graphics, 2023, 28(4):.1019-1028.
- Zhengsen Xu, Haiyan Guan*, Jian Kang, Xiangda Lei, Lingfei Ma, Yongtao Yu, Yiping Chen, Jonathan Li, 2022. Pavement Crack Detection from CCD Images with A Locally Enhanced Transformer Network. Internation Journal of Applied Earth Observation and Geoinformation, 110: 102825.
- Zhengsen Xu, Haiyan Guan*, Daifeng Peng, Haohao Zhao, Yongtao Yu, Xiangda Lei, Yongtao Yu, 2022. A dual-attention capsule network for building extraction from high-resolution remote sensing imagery. National Remote Sensing Bulletin, 2022, 26(08):1636-1649.
- Zhengsen Xu, Yongming Xu*. 2021. Study on the Spatio-Temporal Evolution of the Yangtze River Delta Urban Agglomeration by Integrating DMSP/OLS and NPP/VIIRS Nighttime Light Data. Journal of Geo-information Science, 23(5):837-849.