ZHIMENG HE

Room 417, Main Building East Quad., School of Geographical & Earth Sciences

zhimeng.he@glasgow.ac.uk

Research title: AI-based Extraction of Building Rooftops to Support Indigenous Community Planning in Canadian North

Research Summary

My research primarily focuses on leveraging advanced deep learning architectures to enhance the extraction of building rooftops from high-resolution orthophotos. I am particularly interested in integrating Transformer architectures, involution, and E-Unet to address the challenge of extracting precise building contours in complex urban environments. My current work involves experimenting with these models to improve the accuracy of building footprint extraction, particularly on large-scale datasets such as the Waterloo Building Dataset and the WHU Massachusetts Buildings Dataset.

Moreover, I have a keen interest in exploring the applications of 3D data in urban modeling and its broader utilization in autonomous driving systems. This includes employing 3D point cloud data and LiDAR technology to enhance scene understanding and improve the perception capabilities of autonomous vehicles. My research is progressively transitioning towards multidimensional data fusion and its applications in urban infrastructure analysis and real-time decision-making for autonomous vehicles.

Through my work, I aim to combine cutting-edge deep learning innovations with practical applications in urban environments and intelligent transportation systems, making contributions to the fields of remote sensing, 3D data analysis, and autonomous driving.

Publications

  • Z. He, Y. Cai, H. He, X. Xian and B. Barrett, "An Enhanced Trans-Involution Network for Building Footprint Extraction from High Resolution Orthoimagery," IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 2024, pp. 10030-10034, doi: 10.1109/IGARSS53475.2024.10640523.
  • Cai Y, He H, He Z, et al. Enhancing Spatial Resolution of Building Datasets Using Transformer-Based Single-Image Super-Resolution[C]//IGARSS 2023-2023 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2023: 6338-6341.
  • He, Z., He, H., Li, J., Chapman, M. A., and Ding, H.: A SHORT-CUT CONNECTIONS-BASED NEURAL NETWORK FOR BUILDING EXTRACTION FROM HIGH RESOLUTION ORTHOIMAGERY, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B1-2022, 39–44, https://doi.org/10.5194/isprs-archives-XLIII-B1-2022-39-2022, 2022.
  • HE Zhimeng, DING Haiyong, AN Bingqi. E-Unet: a atrous convolution-based neural network for building extraction from high-resolution remote sensing images[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(3): 457-467.
  • Zheng L, He Z, Ding H. Research on the Sparse Plastic Shed Extraction from High Resolution Images Using ENVINet 5 Deep Learning Method[J]. Remote Sensing Technology and Application, 2021, 36(4): 908-915.

Supervisors

Grants

  •  Doctoral Studies: Pursuing a Ph.D. at the University of Glasgow, UK, funded by the China Scholarship Council (CSC) with a study period of four years.

  • 2024: Received the IEEE Geoscience and Remote Sensing Society Travel Grant to attend the 2024 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), held from July 7 to 12, 2024, in Athens, Greece.

  • April 2024: Awarded Research Enabling Funding for Ph.D. studies at the University of Glasgow.

  • 2020, 2021, 2022: Recipient of the Third-Class Master's Degree Scholarship at Nanjing University of Information Science and Technology (NUIST), China.

  • 2019: Recognized as an Outstanding Bachelor's Degree Graduate of Nanjing University of Information Science and Technology (NUIST).

  • 2017: Awarded the Jiangsu Government Scholarship for overseas study in Geographic Information Science at Saint Louis University, USA.

 

Conference

  • Poster Presentation: 2024 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), July 7–12, 2024, Athens, Greece.
  • Oral Presentation: International Society for Photogrammetry and Remote Sensing (ISPRS), June 6–11, 2022, Nice, France.

Teaching

2024-2025 Academic Year:

  • EARTH4071 - Sedimentary Environments: Lab demonstrator with a focus on QGIS usage.
  • EARTH2010 - Earth Science (2A): Lab demonstrator focusing on sediments and sustainability.
  • Geography 1: Demonstrator responsible for QGIS usage and fieldwork activities.
  • Geography 2: Demonstrator for Statistics and GIS Labs (Semester 1), using Excel and Python.
  • Summer School 2024: Demonstrator.

2023-2024 Academic Year:

  • Geography 1: Demonstrator responsible for grading assignments.