Low-Cost Deep Learning for Building Detection with Application to Informal Urban Planning

This article studies the application of deep neural networks for automatic building detection in aerial RGB images. Special focus is put on accuracy robustness in both well-structured and poorly planned urban scenarios, which pose significant challenges due to occlusions, irregular building layouts, and limited contextual cues. The applied methodology considers several CNNs using only RBG images as input, and both validation and transfer capabilities are studied. U-Net-based models achieve the highest single-model accuracy, with an Intersection over Union (IoU) of 0.9101. A soft-voting ensemble of the best U-Net models further increases performance, reaching a best ensemble IoU of 0.9665, improving over state-of-the-art building detection methods on standard benchmarks. The approach demonstrates strong generalization using only RGB imagery, supporting scalable, low-cost applications in urban planning and geospatial analysis

Convolutional neural network · Deep learning · Geospatial analysis · RGB color model · Transfer of learning · Urban planning · Advanced Neural Network Applications · Remote Sensing and LiDAR Applications · Remote-Sensing Image Classification

• Fully convolutional networks for semantic segmentation

  Jonathan Long, Evan Shelhamer et al.•2015 IEEE Conference on Computer…•2015

  Add to list

• Recognition and Classification of Typical Building Shapes Based on Yolo Object Detection Models

  Open Access•Xiao Wang, Haizhong Qian et al.•ISPRS International Journal of…•2024

  Add to list

• Automatic Building Detection with Polygonizing and Attribute Extraction from High-Resolution Images

  Open Access•Samitha Daranagama, Apichon Witayangkurn•ISPRS International Journal of…•2021

  Add to list

• A Building Group Recognition Method Integrating Spatial and Semantic Similarity

  Open Access•Huimin Liu, Wenpei Wang et al.•ISPRS International Journal of…•2025

  Add to list