Translator Disclaimer
18 November 2019 Semantic segmentation on small datasets of satellite images using convolutional neural networks
Author Affiliations +
Abstract

Semantic segmentation is one of the most popular and challenging applications of deep learning. It refers to the process of dividing a digital image into semantically homogeneous areas with similar properties. We employ the use of deep learning techniques to perform semantic segmentation on high-resolution satellite images representing urban scenes to identify roads, vegetation, and buildings. A SegNet-based neural network with an encoder–decoder architecture is employed. Despite the small size of the dataset, the results are promising. We show that the network is able to accurately distinguish between these groups for different test images, when using a network with four convolutional layers.

© 2019 Society of Photo-Optical Instrumentation Engineers (SPIE) 1931-3195/2019/$28.00 © 2019 SPIE
Mohammed Chachan Younis and Edward Keedwell "Semantic segmentation on small datasets of satellite images using convolutional neural networks," Journal of Applied Remote Sensing 13(4), 046510 (18 November 2019). https://doi.org/10.1117/1.JRS.13.046510
Received: 2 July 2019; Accepted: 25 October 2019; Published: 18 November 2019
JOURNAL ARTICLE
16 PAGES


SHARE
Advertisement
Advertisement
Back to Top