The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLVI-4/W3-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVI-4/W3-2021, 261–266, 2022
https://doi.org/10.5194/isprs-archives-XLVI-4-W3-2021-261-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVI-4/W3-2021, 261–266, 2022
https://doi.org/10.5194/isprs-archives-XLVI-4-W3-2021-261-2022
 
11 Jan 2022
11 Jan 2022

DEEP LEARNING APPROACH FOR URBAN MAPPING

C. Najjaj, H. Rhinane, and A. Hilali C. Najjaj et al.
  • Geosciences Laboratory, Faculty of Sciences Ain Chock, University Hassan II, Casablanca 20100, Morocco

Keywords: Deep learning approach, Fully Convolutional Network, UNET, Satellite imagery, 25 epochs: Accuracy, ARCGIS

Abstract. Researchers in computer vision and machine learning are becoming increasingly interested in image semantic segmentation. Many methods based on convolutional neural networks (CNNs) have been proposed and have made considerable progress in the building extraction mission. This other methods can result in suboptimal segmentation outcomes. Recently, to extract buildings with a great precision, we propose a model which can recognize all the buildings and present them in mask with white and the other classes in black. This developed network, which is based on U-Net, will boost the model's sensitivity. This paper provides a deep learning approach for building detection on satellite imagery applied in Casablanca city, Firstly, to begin we describe the terminology of this field. Next, the main datasets exposed in this project which’s 1000 satellite imagery. Then, we train the model UNET for 25 epochs on the training and validation datasets and testing the pretrained weight model with some unseen satellite images. Finally, the experimental results show that the proposed model offers good performance obtained as a binary mask that extract all the buildings in the region of Casablanca with a higher accuracy and entirety to achieve an average F1 score on test data of 0.91.