Deforestation detection based on U-Net and LSTM in optical satellite remote sensing images

Jie Zhang; Zhibao Wang; Lu Bai; Guangfu Song; Jinhua Tao; Liangfu Chen

doi:10.1109/IGARSS47720.2021.9554689

Deforestation detection based on U-Net and LSTM in optical satellite remote sensing images

Jie Zhang, Zhibao Wang, Lu Bai, Guangfu Song, Jinhua Tao, Liangfu Chen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

18 Citations (Scopus)

Abstract

The protection and monitoring of forest resources has drawn considerable national attention. Traditional deforestation monitoring requires a lot of manpower and material resources through manual visual interpretation and manual change patterns labelling, which has problems of low efficiency and high missed alarm rate. Therefore, this paper explores the detection for deforestation changes from remote sensing images based on deep learning framework, and aims to help forestry department manage and monitor forest resources. In this paper, an U-Net+LSTM framework is used to detect the changes of deforestation from remote sensing images. The evaluation data is Sentinel-2 dataset and the study area is Guangxi Sanjiang Dong Autonomous County in China. The results show that the F1 score of the framework is as high as 0.715, which proves the proposed model can effectively detect the change from forest to bare soil in remote sensing images.

Original language	English
Title of host publication	2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3753-3756
Number of pages	4
ISBN (Electronic)	9781665403696
ISBN (Print)	9781665447621
DOIs	https://doi.org/10.1109/IGARSS47720.2021.9554689
Publication status	Published - 12 Oct 2021
Externally published	Yes
Event	IEEE International Geoscience and Remote Sensing Symposium 2021 - Brussels, Belgium Duration: 12 Jul 2021 → 16 Jul 2021

Publication series

Name	IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings
ISSN (Print)	2153-6996
ISSN (Electronic)	2153-7003

Conference

Conference	IEEE International Geoscience and Remote Sensing Symposium 2021
Abbreviated title	IGARSS 2021
Country/Territory	Belgium
City	Brussels
Period	12/07/2021 → 16/07/2021

Bibliographical note

Funding Information:
This work was supported in part by TUOHAI special project 2020 from Bohai Rim Energy Research Institute of Northeast Petroleum University under Grant HBHZX202002 and project of Excellent and Middle-aged Scientific Research Innovation Team of Northeast Petroleum University under Grant KYCXTD201903.

Publisher Copyright:
© 2021 IEEE.

Keywords

change detection
deep learning
LSTM
Remote sensing
U-Net

ASJC Scopus subject areas

Computer Science Applications
General Earth and Planetary Sciences

Access to Document

10.1109/IGARSS47720.2021.9554689Licence: Unspecified

Cite this

Zhang, J., Wang, Z., Bai, L., Song, G., Tao, J., & Chen, L. (2021). Deforestation detection based on U-Net and LSTM in optical satellite remote sensing images. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings (pp. 3753-3756). (IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS47720.2021.9554689

Zhang, Jie ; Wang, Zhibao ; Bai, Lu et al. / Deforestation detection based on U-Net and LSTM in optical satellite remote sensing images. 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 3753-3756 (IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings).

@inproceedings{24c600bf74b04279a0b7bb7e829bb40e,

title = "Deforestation detection based on U-Net and LSTM in optical satellite remote sensing images",

abstract = "The protection and monitoring of forest resources has drawn considerable national attention. Traditional deforestation monitoring requires a lot of manpower and material resources through manual visual interpretation and manual change patterns labelling, which has problems of low efficiency and high missed alarm rate. Therefore, this paper explores the detection for deforestation changes from remote sensing images based on deep learning framework, and aims to help forestry department manage and monitor forest resources. In this paper, an U-Net+LSTM framework is used to detect the changes of deforestation from remote sensing images. The evaluation data is Sentinel-2 dataset and the study area is Guangxi Sanjiang Dong Autonomous County in China. The results show that the F1 score of the framework is as high as 0.715, which proves the proposed model can effectively detect the change from forest to bare soil in remote sensing images.",

keywords = "change detection, deep learning, LSTM, Remote sensing, U-Net",

author = "Jie Zhang and Zhibao Wang and Lu Bai and Guangfu Song and Jinhua Tao and Liangfu Chen",

note = "Funding Information: This work was supported in part by TUOHAI special project 2020 from Bohai Rim Energy Research Institute of Northeast Petroleum University under Grant HBHZX202002 and project of Excellent and Middle-aged Scientific Research Innovation Team of Northeast Petroleum University under Grant KYCXTD201903. Publisher Copyright: {\textcopyright} 2021 IEEE.; IEEE International Geoscience and Remote Sensing Symposium 2021, IGARSS 2021 ; Conference date: 12-07-2021 Through 16-07-2021",

year = "2021",

month = oct,

day = "12",

doi = "10.1109/IGARSS47720.2021.9554689",

language = "English",

isbn = "9781665447621",

series = "IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3753--3756",

booktitle = "2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings",

address = "United States",

}

Zhang, J, Wang, Z, Bai, L, Song, G, Tao, J & Chen, L 2021, Deforestation detection based on U-Net and LSTM in optical satellite remote sensing images. in 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings. IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 3753-3756, IEEE International Geoscience and Remote Sensing Symposium 2021, Brussels, Belgium, 12/07/2021. https://doi.org/10.1109/IGARSS47720.2021.9554689

Deforestation detection based on U-Net and LSTM in optical satellite remote sensing images. / Zhang, Jie; Wang, Zhibao; Bai, Lu et al.
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. p. 3753-3756 (IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Deforestation detection based on U-Net and LSTM in optical satellite remote sensing images

AU - Zhang, Jie

AU - Wang, Zhibao

AU - Bai, Lu

AU - Song, Guangfu

AU - Tao, Jinhua

AU - Chen, Liangfu

N1 - Funding Information: This work was supported in part by TUOHAI special project 2020 from Bohai Rim Energy Research Institute of Northeast Petroleum University under Grant HBHZX202002 and project of Excellent and Middle-aged Scientific Research Innovation Team of Northeast Petroleum University under Grant KYCXTD201903. Publisher Copyright: © 2021 IEEE.

PY - 2021/10/12

Y1 - 2021/10/12

N2 - The protection and monitoring of forest resources has drawn considerable national attention. Traditional deforestation monitoring requires a lot of manpower and material resources through manual visual interpretation and manual change patterns labelling, which has problems of low efficiency and high missed alarm rate. Therefore, this paper explores the detection for deforestation changes from remote sensing images based on deep learning framework, and aims to help forestry department manage and monitor forest resources. In this paper, an U-Net+LSTM framework is used to detect the changes of deforestation from remote sensing images. The evaluation data is Sentinel-2 dataset and the study area is Guangxi Sanjiang Dong Autonomous County in China. The results show that the F1 score of the framework is as high as 0.715, which proves the proposed model can effectively detect the change from forest to bare soil in remote sensing images.

AB - The protection and monitoring of forest resources has drawn considerable national attention. Traditional deforestation monitoring requires a lot of manpower and material resources through manual visual interpretation and manual change patterns labelling, which has problems of low efficiency and high missed alarm rate. Therefore, this paper explores the detection for deforestation changes from remote sensing images based on deep learning framework, and aims to help forestry department manage and monitor forest resources. In this paper, an U-Net+LSTM framework is used to detect the changes of deforestation from remote sensing images. The evaluation data is Sentinel-2 dataset and the study area is Guangxi Sanjiang Dong Autonomous County in China. The results show that the F1 score of the framework is as high as 0.715, which proves the proposed model can effectively detect the change from forest to bare soil in remote sensing images.

KW - change detection

KW - deep learning

KW - LSTM

KW - Remote sensing

KW - U-Net

U2 - 10.1109/IGARSS47720.2021.9554689

DO - 10.1109/IGARSS47720.2021.9554689

M3 - Conference contribution

AN - SCOPUS:85129812949

SN - 9781665447621

T3 - IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings

SP - 3753

EP - 3756

BT - 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE International Geoscience and Remote Sensing Symposium 2021

Y2 - 12 July 2021 through 16 July 2021

ER -

Zhang J, Wang Z, Bai L, Song G, Tao J, Chen L. Deforestation detection based on U-Net and LSTM in optical satellite remote sensing images. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings. Institute of Electrical and Electronics Engineers Inc. 2021. p. 3753-3756. (IEEE International Geoscience and Remote Sensing Symposium IGARSS: proceedings). doi: 10.1109/IGARSS47720.2021.9554689

Deforestation detection based on U-Net and LSTM in optical satellite remote sensing images

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this