Rate My Professor Hao Cheng

Hao Cheng is an Assistant Professor in the Department of Earth Observation Science at the ITC Faculty of Geo-Information Science and Earth Observation, University of Twente, Netherlands, a position he has held since 2024. He previously served as a Marie Skłodowska-Curie Actions postdoctoral fellow at the same institution on the VeVuSafety project, focusing on learning interactions between vehicles and vulnerable road users for safer Intelligent Transportation Systems and Autonomous Driving. Prior to joining University of Twente, Cheng was a postdoctoral researcher at the Institute of Cartography and Geoinformatics, Leibniz University Hannover, Germany. He earned his Ph.D. with distinction in Civil Engineering and Geodetic Science from the Faculty of Civil Engineering and Geodetic Science, Leibniz University Hannover, in 2021, and his M.Sc. with distinction in Internet Technologies and Information Systems from TU Braunschweig, Leibniz University Hannover, TU Clausthal, and University Göttingen, Germany, in 2017.

Cheng's research interests encompass accessible and responsible GeoAI, deep learning for road user behavior modeling in Intelligent Transport Systems and Autonomous Driving, safety analysis between vehicles and vulnerable road users, and focuses on perception, reconstruction, and motion modeling. His expertise spans ethical dimensions of AI, computer vision, autonomous agent systems, human-AI interaction, machine learning, and geo-sciences. Key publications include 'Gaussian on-the-fly splatting: A progressive framework for robust near real-time 3DGS optimization' (2026, IEEE Robotics and Automation Letters), 'Explainable few-shot learning workflow for detecting invasive and exotic tree species' (2025, Scientific Reports), 'LDPoly: Latent diffusion for polygonal road outline extraction in large-scale topographic mapping' (2025, ISPRS Journal of Photogrammetry and Remote Sensing), 'RoIPoly: Vectorized building outline extraction using vertex and logit embeddings' (2025, ISPRS Journal of Photogrammetry and Remote Sensing), 'T-Graph: Enhancing sparse-view camera pose estimation by pairwise translation graph' (2025, ISPRS Journal), 'DVLO4D: Deep Visual-Lidar Odometry with Sparse Spatial-Temporal Fusion' (2025, IEEE ICRA), 'LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints' (2024, IEEE CVPRW), 'Feature Pyramid biLSTM: Using Smartphone Sensors for Transportation Mode Detection' (2024, Transportation Research Interdisciplinary Perspectives), 'Gatraj: A graph-and attention-based multi-agent trajectory prediction model' (2023, ISPRS Journal of Photogrammetry and Remote Sensing), and 'Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving' (2022, IEEE Robotics and Automation Letters). Cheng has been recognized as a top reviewer for the ISPRS Journal of Photogrammetry and Remote Sensing in 2024 and 2025, and received a best paper award in 2023. His work contributes to UN Sustainable Development Goals 9 (Industry, Innovation, and Infrastructure) and 11 (Sustainable Cities and Communities).