Super-Resolution for “Jilin-1” Satellite Video Imagery via a Convolutional Network
Super-resolution for satellite video attaches much significance to earth observation accuracy, and the special imaging and transmission conditions on the video satellite pose great challenges to this task. The existing deep convolutional neural-network-based methods require pre-processing or post-pr...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/18/4/1194 |
_version_ | 1797999987812990976 |
---|---|
author | Aoran Xiao Zhongyuan Wang Lei Wang Yexian Ren |
author_facet | Aoran Xiao Zhongyuan Wang Lei Wang Yexian Ren |
author_sort | Aoran Xiao |
collection | DOAJ |
description | Super-resolution for satellite video attaches much significance to earth observation accuracy, and the special imaging and transmission conditions on the video satellite pose great challenges to this task. The existing deep convolutional neural-network-based methods require pre-processing or post-processing to be adapted to a high-resolution size or pixel format, leading to reduced performance and extra complexity. To this end, this paper proposes a five-layer end-to-end network structure without any pre-processing and post-processing, but imposes a reshape or deconvolution layer at the end of the network to retain the distribution of ground objects within the image. Meanwhile, we formulate a joint loss function by combining the output and high-dimensional features of a non-linear mapping network to precisely learn the desirable mapping relationship between low-resolution images and their high-resolution counterparts. Also, we use satellite video data itself as a training set, which favors consistency between training and testing images and promotes the method’s practicality. Experimental results on “Jilin-1” satellite video imagery show that this method demonstrates a superior performance in terms of both visual effects and measure metrics over competing methods. |
first_indexed | 2024-04-11T11:13:06Z |
format | Article |
id | doaj.art-ac55b28be905413c912b833aa0c98bfc |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-11T11:13:06Z |
publishDate | 2018-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-ac55b28be905413c912b833aa0c98bfc2022-12-22T04:27:25ZengMDPI AGSensors1424-82202018-04-01184119410.3390/s18041194s18041194Super-Resolution for “Jilin-1” Satellite Video Imagery via a Convolutional NetworkAoran Xiao0Zhongyuan Wang1Lei Wang2Yexian Ren3State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan 430079, ChinaNational Engineering Research Center for Multimedia Software, School of Computer, Wuhan University, Wuhan 430072, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan 430079, ChinaSuper-resolution for satellite video attaches much significance to earth observation accuracy, and the special imaging and transmission conditions on the video satellite pose great challenges to this task. The existing deep convolutional neural-network-based methods require pre-processing or post-processing to be adapted to a high-resolution size or pixel format, leading to reduced performance and extra complexity. To this end, this paper proposes a five-layer end-to-end network structure without any pre-processing and post-processing, but imposes a reshape or deconvolution layer at the end of the network to retain the distribution of ground objects within the image. Meanwhile, we formulate a joint loss function by combining the output and high-dimensional features of a non-linear mapping network to precisely learn the desirable mapping relationship between low-resolution images and their high-resolution counterparts. Also, we use satellite video data itself as a training set, which favors consistency between training and testing images and promotes the method’s practicality. Experimental results on “Jilin-1” satellite video imagery show that this method demonstrates a superior performance in terms of both visual effects and measure metrics over competing methods.http://www.mdpi.com/1424-8220/18/4/1194super-resolutionvideo satellitedeep convolutional network |
spellingShingle | Aoran Xiao Zhongyuan Wang Lei Wang Yexian Ren Super-Resolution for “Jilin-1” Satellite Video Imagery via a Convolutional Network Sensors super-resolution video satellite deep convolutional network |
title | Super-Resolution for “Jilin-1” Satellite Video Imagery via a Convolutional Network |
title_full | Super-Resolution for “Jilin-1” Satellite Video Imagery via a Convolutional Network |
title_fullStr | Super-Resolution for “Jilin-1” Satellite Video Imagery via a Convolutional Network |
title_full_unstemmed | Super-Resolution for “Jilin-1” Satellite Video Imagery via a Convolutional Network |
title_short | Super-Resolution for “Jilin-1” Satellite Video Imagery via a Convolutional Network |
title_sort | super resolution for jilin 1 satellite video imagery via a convolutional network |
topic | super-resolution video satellite deep convolutional network |
url | http://www.mdpi.com/1424-8220/18/4/1194 |
work_keys_str_mv | AT aoranxiao superresolutionforjilin1satellitevideoimageryviaaconvolutionalnetwork AT zhongyuanwang superresolutionforjilin1satellitevideoimageryviaaconvolutionalnetwork AT leiwang superresolutionforjilin1satellitevideoimageryviaaconvolutionalnetwork AT yexianren superresolutionforjilin1satellitevideoimageryviaaconvolutionalnetwork |