Evaluating Image Normalization via GANs for Environmental Mapping: A Case Study of Lichen Mapping Using High-Resolution Satellite Imagery
Illumination variations in non-atmospherically corrected high-resolution satellite (HRS) images acquired at different dates/times/locations pose a major challenge for large-area environmental mapping and monitoring. This problem is exacerbated in cases where a classification model is trained only on...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/24/5035 |
| _version_ | 1827669856159268864 |
|---|---|
| author | Shahab Jozdani Dongmei Chen Wenjun Chen Sylvain G. Leblanc Julie Lovitt Liming He Robert H. Fraser Brian Alan Johnson |
| author_facet | Shahab Jozdani Dongmei Chen Wenjun Chen Sylvain G. Leblanc Julie Lovitt Liming He Robert H. Fraser Brian Alan Johnson |
| author_sort | Shahab Jozdani |
| collection | DOAJ |
| description | Illumination variations in non-atmospherically corrected high-resolution satellite (HRS) images acquired at different dates/times/locations pose a major challenge for large-area environmental mapping and monitoring. This problem is exacerbated in cases where a classification model is trained only on one image (and often limited training data) but applied to other scenes without collecting additional samples from these new images. In this research, by focusing on caribou lichen mapping, we evaluated the potential of using conditional Generative Adversarial Networks (cGANs) for the normalization of WorldView-2 (WV2) images of one area to a source WV2 image of another area on which a lichen detector model was trained. In this regard, we considered an extreme case where the classifier was not fine-tuned on the normalized images. We tested two main scenarios to normalize four target WV2 images to a source 50 cm pansharpened WV2 image: (1) normalizing based only on the WV2 panchromatic band, and (2) normalizing based on the WV2 panchromatic band and Sentinel-2 surface reflectance (SR) imagery. Our experiments showed that normalizing even based only on the WV2 panchromatic band led to a significant lichen-detection accuracy improvement compared to the use of original pansharpened target images. However, we found that conditioning the cGAN on both the WV2 panchromatic band and auxiliary information (in this case, Sentinel-2 SR imagery) further improved normalization and the subsequent classification results due to adding a more invariant source of information. Our experiments showed that, using only the panchromatic band, F1-score values ranged from 54% to 88%, while using the fused panchromatic and SR, F1-score values ranged from 75% to 91%. |
| first_indexed | 2024-03-10T03:11:55Z |
| format | Article |
| id | doaj.art-be0d970c11b44d03b72c6716a071eb73 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:11:55Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-be0d970c11b44d03b72c6716a071eb732023-11-23T10:23:56ZengMDPI AGRemote Sensing2072-42922021-12-011324503510.3390/rs13245035Evaluating Image Normalization via GANs for Environmental Mapping: A Case Study of Lichen Mapping Using High-Resolution Satellite ImageryShahab Jozdani0Dongmei Chen1Wenjun Chen2Sylvain G. Leblanc3Julie Lovitt4Liming He5Robert H. Fraser6Brian Alan Johnson7Department of Geography and Planning, Queen’s University, Kingston, ON K7L 3N6, CanadaDepartment of Geography and Planning, Queen’s University, Kingston, ON K7L 3N6, CanadaCanada Centre for Remote Sensing, Natural Resources Canada, 560 Rochester Street, Ottawa, ON K1S 5K2, CanadaCanada Centre for Remote Sensing, Natural Resources Canada, 560 Rochester Street, Ottawa, ON K1S 5K2, CanadaCanada Centre for Remote Sensing, Natural Resources Canada, 560 Rochester Street, Ottawa, ON K1S 5K2, CanadaCanada Centre for Remote Sensing, Natural Resources Canada, 560 Rochester Street, Ottawa, ON K1S 5K2, CanadaCanada Centre for Remote Sensing, Natural Resources Canada, 560 Rochester Street, Ottawa, ON K1S 5K2, CanadaNatural Resources and Ecosystem Services Area, Institute for Global Environmental Strategies, 2108-1 Kamiyamaguchi, Hayama 240-0115, Kanagawa, JapanIllumination variations in non-atmospherically corrected high-resolution satellite (HRS) images acquired at different dates/times/locations pose a major challenge for large-area environmental mapping and monitoring. This problem is exacerbated in cases where a classification model is trained only on one image (and often limited training data) but applied to other scenes without collecting additional samples from these new images. In this research, by focusing on caribou lichen mapping, we evaluated the potential of using conditional Generative Adversarial Networks (cGANs) for the normalization of WorldView-2 (WV2) images of one area to a source WV2 image of another area on which a lichen detector model was trained. In this regard, we considered an extreme case where the classifier was not fine-tuned on the normalized images. We tested two main scenarios to normalize four target WV2 images to a source 50 cm pansharpened WV2 image: (1) normalizing based only on the WV2 panchromatic band, and (2) normalizing based on the WV2 panchromatic band and Sentinel-2 surface reflectance (SR) imagery. Our experiments showed that normalizing even based only on the WV2 panchromatic band led to a significant lichen-detection accuracy improvement compared to the use of original pansharpened target images. However, we found that conditioning the cGAN on both the WV2 panchromatic band and auxiliary information (in this case, Sentinel-2 SR imagery) further improved normalization and the subsequent classification results due to adding a more invariant source of information. Our experiments showed that, using only the panchromatic band, F1-score values ranged from 54% to 88%, while using the fused panchromatic and SR, F1-score values ranged from 75% to 91%.https://www.mdpi.com/2072-4292/13/24/5035remote sensingGANsimage normalizationdeep learninglichen mappingenvironmental mapping |
| spellingShingle | Shahab Jozdani Dongmei Chen Wenjun Chen Sylvain G. Leblanc Julie Lovitt Liming He Robert H. Fraser Brian Alan Johnson Evaluating Image Normalization via GANs for Environmental Mapping: A Case Study of Lichen Mapping Using High-Resolution Satellite Imagery Remote Sensing remote sensing GANs image normalization deep learning lichen mapping environmental mapping |
| title | Evaluating Image Normalization via GANs for Environmental Mapping: A Case Study of Lichen Mapping Using High-Resolution Satellite Imagery |
| title_full | Evaluating Image Normalization via GANs for Environmental Mapping: A Case Study of Lichen Mapping Using High-Resolution Satellite Imagery |
| title_fullStr | Evaluating Image Normalization via GANs for Environmental Mapping: A Case Study of Lichen Mapping Using High-Resolution Satellite Imagery |
| title_full_unstemmed | Evaluating Image Normalization via GANs for Environmental Mapping: A Case Study of Lichen Mapping Using High-Resolution Satellite Imagery |
| title_short | Evaluating Image Normalization via GANs for Environmental Mapping: A Case Study of Lichen Mapping Using High-Resolution Satellite Imagery |
| title_sort | evaluating image normalization via gans for environmental mapping a case study of lichen mapping using high resolution satellite imagery |
| topic | remote sensing GANs image normalization deep learning lichen mapping environmental mapping |
| url | https://www.mdpi.com/2072-4292/13/24/5035 |
| work_keys_str_mv | AT shahabjozdani evaluatingimagenormalizationviagansforenvironmentalmappingacasestudyoflichenmappingusinghighresolutionsatelliteimagery AT dongmeichen evaluatingimagenormalizationviagansforenvironmentalmappingacasestudyoflichenmappingusinghighresolutionsatelliteimagery AT wenjunchen evaluatingimagenormalizationviagansforenvironmentalmappingacasestudyoflichenmappingusinghighresolutionsatelliteimagery AT sylvaingleblanc evaluatingimagenormalizationviagansforenvironmentalmappingacasestudyoflichenmappingusinghighresolutionsatelliteimagery AT julielovitt evaluatingimagenormalizationviagansforenvironmentalmappingacasestudyoflichenmappingusinghighresolutionsatelliteimagery AT liminghe evaluatingimagenormalizationviagansforenvironmentalmappingacasestudyoflichenmappingusinghighresolutionsatelliteimagery AT roberthfraser evaluatingimagenormalizationviagansforenvironmentalmappingacasestudyoflichenmappingusinghighresolutionsatelliteimagery AT brianalanjohnson evaluatingimagenormalizationviagansforenvironmentalmappingacasestudyoflichenmappingusinghighresolutionsatelliteimagery |