Semi-Supervised Change Detection of Small Water Bodies Using Rgb and Multispectral Images in Peruvian Rainforests

Kangning CUI; Seda CAMALAN; Ruoning LI; Victor Paul PAUCA; Sarra ALQAHTANI; Robert PLEMMONS; Miles SILMAN; Evan Nylen DETHIER; David LUTZ; Raymond CHAN

doi:10.1109/WHISPERS56178.2022.9955140

Semi-Supervised Change Detection of Small Water Bodies Using Rgb and Multispectral Images in Peruvian Rainforests

Kangning CUI, Seda CAMALAN, Ruoning LI, Victor Paul PAUCA, Sarra ALQAHTANI, Robert PLEMMONS, Miles SILMAN, Evan Nylen DETHIER, David LUTZ, Raymond CHAN^*

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

5 Citations (Scopus)

Abstract

Artisanal and Small-scale Gold Mining (ASGM) is an important source of income for many households, but it can have large social and environmental effects, especially in rainforests of developing countries. The Sentinel-2 satellites collect multispectral images that can be used for the purpose of detecting changes in water extent and quality which indicates the locations of mining sites. This work focuses on the recognition of ASGM activities in Peruvian Amazon rainforests. We tested several semi-supervised classifiers based on Support Vector Machines (SVMs) to detect the changes of water bodies from 2019 to 2021 in the Madre de Dios region, which is one of the global hotspots of ASGM activities. Experiments show that SVM-based models can achieve reasonable performance for both RGB (using Cohen's κ 0.49) and 6-channel images (using Cohen's κ 0.71) with very limited annotations. The efficacy of incorporating Lab color space for change detection is analyzed as well.

Original language	English
Title of host publication	2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2022
Publisher	IEEE
Number of pages	5
ISBN (Electronic)	9781665470698
DOIs	https://doi.org/10.1109/WHISPERS56178.2022.9955140
Publication status	Published - 2022
Externally published	Yes
Event	12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2022 - Rome, Italy Duration: 13 Sept 2022 → 16 Sept 2022

Publication series

Name	Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing
Volume	2022-September
ISSN (Print)	2158-6276

Conference

Conference	12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2022
Country/Territory	Italy
City	Rome
Period	13/09/22 → 16/09/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

artisanal gold mining
change detection
RGB & multispectral images
semi-manual labeling
semi-supervised machine learning.

Access to Document

10.1109/WHISPERS56178.2022.9955140

Cite this

CUI, K., CAMALAN, S., LI, R., PAUCA, V. P., ALQAHTANI, S., PLEMMONS, R., SILMAN, M., DETHIER, E. N., LUTZ, D., & CHAN, R. (2022). Semi-Supervised Change Detection of Small Water Bodies Using Rgb and Multispectral Images in Peruvian Rainforests. In 2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2022 (Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing; Vol. 2022-September). IEEE. https://doi.org/10.1109/WHISPERS56178.2022.9955140

CUI, Kangning ; CAMALAN, Seda ; LI, Ruoning et al. / Semi-Supervised Change Detection of Small Water Bodies Using Rgb and Multispectral Images in Peruvian Rainforests. 2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2022. IEEE, 2022. (Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing).

@inproceedings{dc3d2d3c00584be495459c39f65bb4b4,

title = "Semi-Supervised Change Detection of Small Water Bodies Using Rgb and Multispectral Images in Peruvian Rainforests",

abstract = "Artisanal and Small-scale Gold Mining (ASGM) is an important source of income for many households, but it can have large social and environmental effects, especially in rainforests of developing countries. The Sentinel-2 satellites collect multispectral images that can be used for the purpose of detecting changes in water extent and quality which indicates the locations of mining sites. This work focuses on the recognition of ASGM activities in Peruvian Amazon rainforests. We tested several semi-supervised classifiers based on Support Vector Machines (SVMs) to detect the changes of water bodies from 2019 to 2021 in the Madre de Dios region, which is one of the global hotspots of ASGM activities. Experiments show that SVM-based models can achieve reasonable performance for both RGB (using Cohen's κ 0.49) and 6-channel images (using Cohen's κ 0.71) with very limited annotations. The efficacy of incorporating Lab color space for change detection is analyzed as well.",

keywords = "artisanal gold mining, change detection, RGB & multispectral images, semi-manual labeling, semi-supervised machine learning.",

author = "Kangning CUI and Seda CAMALAN and Ruoning LI and PAUCA, {Victor Paul} and Sarra ALQAHTANI and Robert PLEMMONS and Miles SILMAN and DETHIER, {Evan Nylen} and David LUTZ and Raymond CHAN",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2022 ; Conference date: 13-09-2022 Through 16-09-2022",

year = "2022",

doi = "10.1109/WHISPERS56178.2022.9955140",

language = "English",

series = "Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing",

publisher = "IEEE",

booktitle = "2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2022",

}

CUI, K, CAMALAN, S, LI, R, PAUCA, VP, ALQAHTANI, S, PLEMMONS, R, SILMAN, M, DETHIER, EN, LUTZ, D & CHAN, R 2022, Semi-Supervised Change Detection of Small Water Bodies Using Rgb and Multispectral Images in Peruvian Rainforests. in 2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2022. Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing, vol. 2022-September, IEEE, 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2022, Rome, Italy, 13/09/22. https://doi.org/10.1109/WHISPERS56178.2022.9955140

Semi-Supervised Change Detection of Small Water Bodies Using Rgb and Multispectral Images in Peruvian Rainforests. / CUI, Kangning; CAMALAN, Seda; LI, Ruoning et al.
2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2022. IEEE, 2022. (Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing; Vol. 2022-September).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - Semi-Supervised Change Detection of Small Water Bodies Using Rgb and Multispectral Images in Peruvian Rainforests

AU - CUI, Kangning

AU - CAMALAN, Seda

AU - LI, Ruoning

AU - PAUCA, Victor Paul

AU - ALQAHTANI, Sarra

AU - PLEMMONS, Robert

AU - SILMAN, Miles

AU - DETHIER, Evan Nylen

AU - LUTZ, David

AU - CHAN, Raymond

PY - 2022

Y1 - 2022

N2 - Artisanal and Small-scale Gold Mining (ASGM) is an important source of income for many households, but it can have large social and environmental effects, especially in rainforests of developing countries. The Sentinel-2 satellites collect multispectral images that can be used for the purpose of detecting changes in water extent and quality which indicates the locations of mining sites. This work focuses on the recognition of ASGM activities in Peruvian Amazon rainforests. We tested several semi-supervised classifiers based on Support Vector Machines (SVMs) to detect the changes of water bodies from 2019 to 2021 in the Madre de Dios region, which is one of the global hotspots of ASGM activities. Experiments show that SVM-based models can achieve reasonable performance for both RGB (using Cohen's κ 0.49) and 6-channel images (using Cohen's κ 0.71) with very limited annotations. The efficacy of incorporating Lab color space for change detection is analyzed as well.

AB - Artisanal and Small-scale Gold Mining (ASGM) is an important source of income for many households, but it can have large social and environmental effects, especially in rainforests of developing countries. The Sentinel-2 satellites collect multispectral images that can be used for the purpose of detecting changes in water extent and quality which indicates the locations of mining sites. This work focuses on the recognition of ASGM activities in Peruvian Amazon rainforests. We tested several semi-supervised classifiers based on Support Vector Machines (SVMs) to detect the changes of water bodies from 2019 to 2021 in the Madre de Dios region, which is one of the global hotspots of ASGM activities. Experiments show that SVM-based models can achieve reasonable performance for both RGB (using Cohen's κ 0.49) and 6-channel images (using Cohen's κ 0.71) with very limited annotations. The efficacy of incorporating Lab color space for change detection is analyzed as well.

KW - artisanal gold mining

KW - change detection

KW - RGB & multispectral images

KW - semi-manual labeling

KW - semi-supervised machine learning.

UR - http://www.scopus.com/inward/record.url?scp=85143149165&partnerID=8YFLogxK

U2 - 10.1109/WHISPERS56178.2022.9955140

DO - 10.1109/WHISPERS56178.2022.9955140

M3 - Conference paper (refereed)

AN - SCOPUS:85143149165

T3 - Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing

BT - 2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2022

PB - IEEE

T2 - 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2022

Y2 - 13 September 2022 through 16 September 2022

ER -

CUI K, CAMALAN S, LI R, PAUCA VP, ALQAHTANI S, PLEMMONS R et al. Semi-Supervised Change Detection of Small Water Bodies Using Rgb and Multispectral Images in Peruvian Rainforests. In 2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2022. IEEE. 2022. (Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing). doi: 10.1109/WHISPERS56178.2022.9955140

Semi-Supervised Change Detection of Small Water Bodies Using Rgb and Multispectral Images in Peruvian Rainforests

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this