Qingyu Li
This is Qingyu Li’s personal homepage.
A short introduction
I am an assistant professor at the School of Science and Engineering of the Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen). I received my Ph.D. from the Technical University of Munich. My dissertation topic is “Deep Learning for Building Footprint Generation from Optical Imagery.” I received my Bachelor’s degree in Remote Sensing Science and Technology from Wuhan University, China; I obtained my double Master’s Degree, which is (1) ESPACE, Technical University of Munich, Germany, and (2) Photogrammetry and Remote Sensing, Wuhan University, China.
News
Our lab at CUHK-Shenzhen is dedicated to harnessing the power of AI and big data to tackle some of the most pressing issues facing our world today. Our mission is to leverage cutting-edge AI technologies for interdisciplinary research, including areas such as Smart City, Energy Analysis, Climate Change, Disaster Management, etc.
I am actively seeking self-motivated PhD / MPhil students (MPhil-PhD Programme in Computer and Information Engineering in Fall 25) and research assistants. Moreover, postdocs and visiting students are also welcome to apply. Please drop me an email with your CV and transcript through liqingyu@cuhk.edu.cn if interested.
Research Interests:
- Artificial Intelligence
- Remote Sensing
- Computer Vision
- Geospatial analysis
Research Highlights:
- Development of novel deep learning algorithms for building footprint generation
- Development of a novel deep learning algorithm for building height retrieval
- Development of a novel deep learning-based framework for undocumented building detection and its application in urban analysis
- Development of novel deep learning-based frameworks for rooftop solar potential analysis
- Development of novel deep learning-based frameworks for roof greening potential assessment
- Development of a novel framework for building energy simulation
- Development of a novel machine learning-based framework for land cover classification
- Development of a novel machine learning algorithm for change detetction
Selected Journal Publications
Li, Qingyu, Hannes Taubenböck , and Xiao Xiang Zhu. “Identification of the potential for roof greening using remote sensing and deep learning.” Cities 159 (2025): 105782.link
Li, Qingyu, Sebastian Krapf, Lichao Mou, Yilei Shi, and Xiao Xiang Zhu. “Deep learning-based framework for city-scale rooftop solar potential estimation by considering roof superstructures.” Applied Energy 374 (2024): 123839.link
Li, Qingyu, Genyu Xu, and Ziqi Gu. “A novel framework for multi-city building energy simulation: Coupling urban microclimate and energy dynamics at high spatiotemporal resolutions.” Sustainable Cities and Society (2024):105718.link
Li, Qingyu, Lichao Mou, Yao Sun, Yuansheng Hua, Yilei Shi, and Xiao Xiang Zhu. “A Review of Building Extraction from Remote Sensing Imagery: Geometrical Structures and Semantic Attributes.” IEEE Transactions on Geoscience and Remote Sensing 60 (2024): 1-15. link
Li, Qingyu, Lichao Mou, Yuansheng Hua, Yilei Shi, Sining Chen, Yao Sun and Xiao Xiang Zhu. “3DCentripetalNet: Building height retrieval from monocular remote sensing imagery.” International Journal of Applied Earth Observation and Geoinformation 120 (2023): 103311.link
Li, Qingyu, Sebastian Krapf, Yilei Shi, and Xiao Xiang Zhu. “SolarNet: A convolutional neural network-based framework for rooftop solar potential estimation from aerial imagery.” International Journal of Applied Earth Observation and Geoinformation 116 (2023): 103098.link
Li, Qingyu, Hannes Taubenböck, Yilei Shi, Stefan Auer, Robert Roschlaub, Clemens Glock, Anna Kruspe, and Xiao Xiang Zhu. “Identification of undocumented buildings in cadastral data using remote sensing: Construction period, morphology, and landscape.” International Journal of Applied Earth Observation and Geoinformation 112 (2022): 102909.link
Li, Qingyu, Yilei Shi, and Xiao Xiang Zhu. “Semi-supervised building footprint generation with feature and output consistency training.” IEEE Transactions on Geoscience and Remote Sensing (2022). link
Li, Qingyu, Lichao Mou, Yuansheng Hua, Yilei Shi, and Xiao Xiang Zhu. “CrossGeoNet: A Framework for Building Footprint Generation of Label-Scarce Geographical Regions.” International Journal of Applied Earth Observation and Geoinformation 111 (2022): 102824. link
Li, Qingyu, Lichao Mou, Yuansheng Hua, Yilei Shi, and Xiao Xiang Zhu. “Building footprint generation through convolutional neural networks with attraction field representation.” IEEE Transactions on Geoscience and Remote Sensing 60 (2021): 1-17. link
Li, Qingyu, Yilei Shi, Xin Huang, and Xiao Xiang Zhu. “Building footprint generation by integrating convolution neural network with feature pairwise conditional random field (FPCRF).” IEEE Transactions on Geoscience and Remote Sensing 58, no. 11 (2020): 7502-7519. link
Li, Qingyu, Yilei Shi, Stefan Auer, Robert Roschlaub, Karin Möst, Michael Schmitt, Clemens Glock, and Xiaoxiang Zhu. “Detection of Undocumented Building Constructions from Official Geodata Using a Convolutional Neural Network.” Remote Sensing 12, no. 21 (2020): 3537. link
Li, Qingyu, Chunping Qiu, Lei Ma, Michael Schmitt, and Xiao Xiang Zhu. “Mapping the land cover of Africa at 10 m resolution from multi-source remote sensing data with Google Earth Engine.” Remote Sensing 12, no. 4 (2020): 602. link
For more information
More info about Qingyu Li can be found in CV or downloaded CV.