Exploring RAU-net for semantic segmentation of Philippines satellite images in identification of building density

This study explores RAU-Net convolutional network architecture on satellite images by classifying geospatial objects on satellite images such as roofs to help in determining the building density of a specific location. This study developed a satellite image dataset in the Philippines and trained the dataset in an RAU-Net Convolutional Neural Network using Tensorflow Keras API. This study proves that U-Net works with a few datasets and provides acceptable performance scores. Furthermore, a new way to calculate Building Density in terms of Building Coverage Ratio (BCR) using satellite images was also presented in this study. The model and the analysis were integrated into an application that determines the BCR of a specific location through a satellite map.

Download paper here - VoR The Version of Record of this manuscript has been published and is available at International Journal of Remote Sensing 2022-08-18 https://doi.org/10.1080/01431161.2021.1986239

Recommended citation: Joseph Jessie S. Oñate & Marianne Ang-Tolentino (2022) Exploring RAU-net for semantic segmentation of Philippines satellite images in identification of building density, International Journal of Remote Sensing, 43:15-16, 5738-5756, DOI: 10.1080/01431161.2021.1986239