A Pixel-Based Deep Learning Approach for Building Height Estimation From Single SAR Images
Open Access
- 6 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 21279-21294
Abstract
Accurate building height estimation from very high-resolution (VHR) Synthetic Aperture Radar (SAR) imagery plays a pivotal role in urban analysis tasks. This paper presents a pixel-based deep learning (DL) framework for estimating building height maps from single COSMO-SkyMed (CSK) SAR images. Supervised training is provided through a refined normalized Digital Surface Model (nDSM), constructed by fusing public building height data with a globally available DSM baseline using a distance-weighted blending scheme. The proposed architecture features a modified Attention U-Net with dual decoders, specialized for built-up and background areas, and is trained using a Mean Absolute Error (MAE) loss for increased robustness to SAR-specific distortions. The model is evaluated across a multi-continental dataset covering eight cities, and tested under both in-distribution and cross-city out-of-distribution (OOD) conditions. The results show that the approach outperforms recent object-based and multimodal benchmarks, especially in European and American cities, although challenges remain in high-rise Asian metropolises.Keywords
Funding Information
- NextGenerationEU in the framework of a Ph.D. through Action 4, Ministerial Decree (118)
This publication has 30 references indexed in Scilit:
- UB-FineNet: Urban building fine-grained classification network for open-access satellite imagesISPRS Journal of Photogrammetry and Remote Sensing, 2024
- The SAR2Height framework for urban height map reconstruction from single SAR intensity imagesISPRS Journal of Photogrammetry and Remote Sensing, 2024
- A prior knowledge guided deep learning method for building extraction from high-resolution remote sensing imagesUrban Informatics, 2024
- Quality of crowdsourced geospatial building information: A global assessment of OpenStreetMap attributesBuilding and Environment, 2023
- Large-scale building height retrieval from single SAR imagery based on bounding box regression networksISPRS Journal of Photogrammetry and Remote Sensing, 2022
- An Introduction to Climate Change Phenomenon2021
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- 2D building change detection from high resolution satelliteimagery: A two-step hierarchical method based on 3D invariant primitivesPattern Recognition Letters, 2010
- Automatic description of complex buildings from multiple imagesComputer Vision and Image Understanding, 2004
- The Role of Color Attributes and Similarity Grouping in 3-D Building ReconstructionComputer Vision and Image Understanding, 1998