Woodland Labeling in Chenzhou, China, via Deep Learning Approach
In order to complete the task of the woodland census in Chenzhou, China, this paper carries out a remote sensing survey on the terrain of this area to produce a data set, and used deep learning methods to label the woodland. There are two main improvements in our paper: Firstly, this paper comparati...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Atlantis Press
2020-09-01
|
Series: | International Journal of Computational Intelligence Systems |
Subjects: | |
Online Access: | https://www.atlantis-press.com/article/125944628/view |
id |
doaj-a5d94b09bfc44d20af9dc9215ba39bb8 |
---|---|
record_format |
Article |
spelling |
doaj-a5d94b09bfc44d20af9dc9215ba39bb82020-11-25T03:38:21ZengAtlantis PressInternational Journal of Computational Intelligence Systems 1875-68832020-09-0113110.2991/ijcis.d.200910.001Woodland Labeling in Chenzhou, China, via Deep Learning ApproachWei WangYujing YangJi LiYongle HuYanhong LuoXin WangIn order to complete the task of the woodland census in Chenzhou, China, this paper carries out a remote sensing survey on the terrain of this area to produce a data set, and used deep learning methods to label the woodland. There are two main improvements in our paper: Firstly, this paper comparatively analyzes the semantic segmentation effects of different deep learning models on remote sensing image datasets in Chenzhou. Secondly, this paper proposed a dense fully convolutional network (DFCN) which combines dense network with FCN model and achieves good semantic segmentation effect. DFCN method is used to label the woodland in Gaofen-2 (GF-2) remote sensing images in Chenzhou. Under the same experimental conditions, the labeling results are compared with the original FCN, SegNet, dilated convolutional network, and so on. In these experiments, the global pixel accuracy of DFCN is 91.5%, and the prediction accuracy of the “woodland” class is 93%, both of them perform better than that of the other methods. In other indicators, our method also has better performance. Using the method of this paper, we have completed the land feature labeling of Chenzhou area and provided it to customers.https://www.atlantis-press.com/article/125944628/viewWoodland labelingConvolutional networkDeep learningDense fully convolutional network (DFCN) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Wei Wang Yujing Yang Ji Li Yongle Hu Yanhong Luo Xin Wang |
spellingShingle |
Wei Wang Yujing Yang Ji Li Yongle Hu Yanhong Luo Xin Wang Woodland Labeling in Chenzhou, China, via Deep Learning Approach International Journal of Computational Intelligence Systems Woodland labeling Convolutional network Deep learning Dense fully convolutional network (DFCN) |
author_facet |
Wei Wang Yujing Yang Ji Li Yongle Hu Yanhong Luo Xin Wang |
author_sort |
Wei Wang |
title |
Woodland Labeling in Chenzhou, China, via Deep Learning Approach |
title_short |
Woodland Labeling in Chenzhou, China, via Deep Learning Approach |
title_full |
Woodland Labeling in Chenzhou, China, via Deep Learning Approach |
title_fullStr |
Woodland Labeling in Chenzhou, China, via Deep Learning Approach |
title_full_unstemmed |
Woodland Labeling in Chenzhou, China, via Deep Learning Approach |
title_sort |
woodland labeling in chenzhou, china, via deep learning approach |
publisher |
Atlantis Press |
series |
International Journal of Computational Intelligence Systems |
issn |
1875-6883 |
publishDate |
2020-09-01 |
description |
In order to complete the task of the woodland census in Chenzhou, China, this paper carries out a remote sensing survey on the terrain of this area to produce a data set, and used deep learning methods to label the woodland. There are two main improvements in our paper: Firstly, this paper comparatively analyzes the semantic segmentation effects of different deep learning models on remote sensing image datasets in Chenzhou. Secondly, this paper proposed a dense fully convolutional network (DFCN) which combines dense network with FCN model and achieves good semantic segmentation effect. DFCN method is used to label the woodland in Gaofen-2 (GF-2) remote sensing images in Chenzhou. Under the same experimental conditions, the labeling results are compared with the original FCN, SegNet, dilated convolutional network, and so on. In these experiments, the global pixel accuracy of DFCN is 91.5%, and the prediction accuracy of the “woodland” class is 93%, both of them perform better than that of the other methods. In other indicators, our method also has better performance. Using the method of this paper, we have completed the land feature labeling of Chenzhou area and provided it to customers. |
topic |
Woodland labeling Convolutional network Deep learning Dense fully convolutional network (DFCN) |
url |
https://www.atlantis-press.com/article/125944628/view |
work_keys_str_mv |
AT weiwang woodlandlabelinginchenzhouchinaviadeeplearningapproach AT yujingyang woodlandlabelinginchenzhouchinaviadeeplearningapproach AT jili woodlandlabelinginchenzhouchinaviadeeplearningapproach AT yonglehu woodlandlabelinginchenzhouchinaviadeeplearningapproach AT yanhongluo woodlandlabelinginchenzhouchinaviadeeplearningapproach AT xinwang woodlandlabelinginchenzhouchinaviadeeplearningapproach |
_version_ |
1724542580703625216 |