Improving semantic segmentation of high-resolution remote sensing images using Wasserstein generative adversarial network

H. r. Hosseinpour, F. Samadzadegan, F. Dadrass javan, S. Motayyeb

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

15 Downloads (Pure)

Abstract

Semantic segmentation of remote sensing images with high spatial resolution has many applications in a wide range of problems in this field. In recent years, the use of advanced techniques based on fully convolutional neural networks have achieved high and impressive accuracies. However, the labels of different classes are estimated independently in this method. In general, the segmentation effect is too coarse to take the relationship between pixels into account. On the other hand, due to the use of convolution filters and limitations of calculations, the field of view information of these filters will be limited in deep layers. In this study, a method based on generative adversarial network (GAN) is proposed to strengthen spatial vicinity in the output segmentation map. The segmentation model receive assistance from the GAN model in the form of a higher order potential loss. Furthermore, for better stability and performance in model training the Wasserstein GAN is used for optimization of the model. We successfully show an increase in semantic segmentation accuracy using the challenging ISPRS Vaihingen benchmark dataset.
Original languageEnglish
Title of host publicationThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
EditorsM.R. Delavar, R. Ali Abbaspour, S. Farzaneh
Place of PublicationTehran
PublisherCopernicus
Pages45-51
VolumeXLVIII-4/W2-2022
DOIs
Publication statusPublished - 19 Feb 2023
EventGeoSpatial Conference 2022 - virtual, Tehran, Iran, Islamic Republic of
Duration: 19 Feb 202322 Feb 2023
https://www.sru.ac.ir/en/4860-2/

Publication series

NameThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

Conference

ConferenceGeoSpatial Conference 2022
Country/TerritoryIran, Islamic Republic of
CityTehran
Period19/02/2322/02/23
OtherJoint 6th SMPR and 4th GIResearch Conferences
Internet address

Fingerprint

Dive into the research topics of 'Improving semantic segmentation of high-resolution remote sensing images using Wasserstein generative adversarial network'. Together they form a unique fingerprint.

Cite this