Abstract
We present a novel approach for estimating building heights using single street-level images. The method employs EfficientNet, a state-of-the-art neural network, to eliminate the need for additional data like street maps. We compare this new method with existing techniques, focusing on accuracy evaluated through metrics like Mean Absolute Error (MAE). The model is pre-trained on the Cityscapes dataset and fine-tuned on images from Toronto’s 3D Massing dataset. It demonstrates strong accuracy, with an MAE of 1.21 meters, outperforming traditional methods.
Publisher
Network Design Lab - Transport Findings
Reference7 articles.
1. Building height estimation using street-view images, deep-learning, contour processing, and geospatial data;Ala'a Al-Habashna;2021 18th Conference on Robots and Vision (CRV),2021
2. The cityscapes dataset for semantic urban scene understanding;Marius Cordts;Proceedings of the IEEE conference on computer vision and pattern recognition,2016
3. An algorithm to estimate building heights from google street-view imagery using single view metrology across a representational state transfer system;Elkin Díaz;SPIE Proceedings,2016
4. EfficientNet: Rethinking model scaling for convolutional neural networks;Mingxing Tan;36th International Conference on Machine Learning, ICML 2019,2019
5. EfficientNetV2: Smaller models and faster training;Mingxing Tan;Proceedings of Machine Learning Research,2021