Abstract:Developing countries usually lack the proper governance means to generate and regularly update a national rooftop map. Using traditional photogrammetry and surveying methods to produce a building map at the federal level is costly and time consuming. Using earth observation and deep learning methods, we can bridge this gap and propose an automated pipeline to fetch such national urban maps. This paper aims to exploit the power of fully convolutional neural networks for multi-class buildings' instance segmentation to leverage high object-wise accuracy results. Buildings' instance segmentation from sub-meter high-resolution satellite images can be achieved with relatively high pixel-wise metric scores. We detail all engineering steps to replicate this work and ensure highly accurate results in dense and slum areas witnessed in regions that lack proper urban planning in the Global South. We applied a case study of the proposed pipeline to Lebanon and successfully produced the first comprehensive national building footprint map with approximately 1 Million units with an 84% accuracy. The proposed architecture relies on advanced augmentation techniques to overcome dataset scarcity, which is often the case in developing countries.
Abstract:Buildings classification using satellite images is becoming more important for several applications such as damage assessment, resource allocation, and population estimation. We focus, in this work, on buildings damage assessment (BDA) and buildings type classification (BTC) of residential and non-residential buildings. We propose to rely solely on RGB satellite images and follow a 2-stage deep learning-based approach, where first, buildings' footprints are extracted using a semantic segmentation model, followed by classification of the cropped images. Due to the lack of an appropriate dataset for the residential/non-residential building classification, we introduce a new dataset of high-resolution satellite images. We conduct extensive experiments to select the best hyper-parameters, model architecture, and training paradigm, and we propose a new transfer learning-based approach that outperforms classical methods. Finally, we validate the proposed approach on two applications showing excellent accuracy and F1-score metrics.
Abstract:Semantic Segmentation of buildings present in satellite images using encoder-decoder like convolutional neural networks is being achieved with relatively high pixel-wise metric scores. In this paper, we aim to exploit the power of fully convolutional neural networks for an instance segmentation task using extra added classes to the output along with the watershed processing technique to leverage better object-wise metric results. We also show that CutMix mixed data augmentations and the One-Cycle learning rate policy are greater regularization methods to achieve a better fit on the training data and increase performance. Furthermore, Mixed Precision Training provided more flexibility to experiment with bigger networks and batches while maintaining stability and convergence during training. We compare and show the effect of these additional changes throughout our whole pipeline to finally provide a set a tuned hyper-parameters that are proven to perform better.