A new semantic segmentation model for remote sensing images

Xin Wei, Yajing Guo, Xin Gao, Menglong Yan, Xian Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Scopus citations

Abstract

Semantic segmentation for remote sensing images is a critical process in the workflow of object-based image analysis. Recently, convolutional neural networks(CNNs) are powerful visual models that yield hierarchies of features. In this paper, we propose a deep convolutional encoder-decoder model for remote sensing images segmentation. Specifically, we rely on the encoder network to extract the high-level semantic feature of ultra-high resolution images and the decoder network is employed to map the low resolution encoder feature maps to full input resolution feature maps for pixel-wise labeling. Also the fully connected conditional random field (CRF) is integrated into the model so that the network can be trained end-to-end. Experiments on the Vaihingen dataset demonstrate that our model can make promising performance.
Original languageEnglish (US)
Title of host publicationInternational Geoscience and Remote Sensing Symposium (IGARSS)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1776-1779
Number of pages4
ISBN (Print)9781509049516
DOIs
StatePublished - Dec 1 2017
Externally publishedYes

Fingerprint

Dive into the research topics of 'A new semantic segmentation model for remote sensing images'. Together they form a unique fingerprint.

Cite this