Share Email Print
cover

Proceedings Paper • new

Urban scene segmentation using semi-supervised GAN
Author(s): Hamideh Kerdegari; Manzoor Razaak; Vasileios Argyriou; Paolo Remagnino
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Semantic segmentation of remote sensing data such as multispectral imagery has been boosted recently using deep convolutional neural networks (CNN). However, segmentation of multispectral images using supervised machine learning algorithms such as CNN requires a significant number of pixel-level annotated data, often unavailable, making the task extremely challenging. To address this, this paper puts forward a semi-supervised framework, based on generative adversarial networks (GAN). The proposed solution consists of a generator network to provide photo-realistic images as extra training data to a multi-class classifier acting as a discriminator and trained on a small annotated dataset. Performance of the proposed semi-supervised GAN is evaluated on two benchmarks multispectral semantic segmentation datasets collected from urban scenes of Vaihingen and Potsdam. Results indicate that the proposed framework achieves competitive performance compared to state-of-the-art semantic segmentation methods and show the potential of GAN-based methods for the challenging task of multispectral image segmentation.

Paper Details

Date Published: 7 October 2019
PDF: 8 pages
Proc. SPIE 11155, Image and Signal Processing for Remote Sensing XXV, 111551H (7 October 2019); doi: 10.1117/12.2533055
Show Author Affiliations
Hamideh Kerdegari, Kingston Univ. (United Kingdom)
Manzoor Razaak, Kingston Univ. (United Kingdom)
Vasileios Argyriou, Kingston Univ. (United Kingdom)
Paolo Remagnino, Kingston Univ. (United Kingdom)


Published in SPIE Proceedings Vol. 11155:
Image and Signal Processing for Remote Sensing XXV
Lorenzo Bruzzone; Francesca Bovolo, Editor(s)

© SPIE. Terms of Use
Back to Top