GEOSCAN Search Results: Fastlink

GEOSCAN Menu


TitleLeveraging deep neural networks to map caribou lichen in high-resolution satellite images based on a small-scale, noisy UAV-derived map
 
AuthorJozdani, S; Chen, D; Chen, WORCID logo; Leblanc, S GORCID logo; Prévost, C; Lovitt, JORCID logo; He, L; Johnson, B A
SourceRemote Sensing vol. 13, issue 14, 2658, 2021 p. 1-24, https://doi.org/10.3390/rs13142658 Open Access logo Open Access
Image
Year2021
Alt SeriesNatural Resources Canada, Contribution Series 20210345
PublisherMDPI AG
Documentserial
Lang.English
Mediapaper; on-line; digital
File formatpdf; html
ProvinceQuebec
AreaManicouagan Reservoir; Canada
Lat/Long WENS -68.9000 -68.7167 50.6250 50.5833
SubjectsScience and Technology; remote sensing; unmanned aerial vehicles
Illustrationssatellite imagery; location maps; diagrams; tables; graphs
ProgramCanada Centre for Remote Sensing Remote Sensing Science Program - Optical methods and applications
Released2021 07 06
AbstractLichen is an important food source for caribou in Canada. Lichen mapping using remote sensing (RS) images could be a challenging task, however, as lichens generally appear in unevenly distributed, small patches, and could resemble surficial features. Moreover, collecting lichen labeled data (reference data) is expensive, which restricts the application of many robust supervised classification models that generally demand a large quantity of labeled data. The goal of this study was to investigate the potential of using a very-high-spatial resolution (1-cm) lichen map of a small sample site (e.g., generated based on a single UAV scene and using field data) to train a subsequent classifier to map caribou lichen over a much larger area (~0.04 km2 vs. ~195 km2) and a lower spatial resolution image (in this case, a 50-cm WorldView-2 image). The limited labeled data from the sample site were also partially noisy due to spatial and temporal mismatching issues. For this, we deployed a recently proposed Teacher-Student semi-supervised learning (SSL) approach (based on U-Net and U-Net++ networks) involving unlabeled data to assist with improving the model performance. Our experiments showed that it was possible to scale-up the UAV-derived lichen map to the WorldView-2 scale with reasonable accuracy (overall accuracy of 85.28% and F1-socre of 84.38%) without collecting any samples directly in the WorldView-2 scene. We also found that our noisy labels were partially beneficial to the SSL robustness because they improved the false positive rate compared to the use of a cleaner training set directly collected within the same area in the WorldView-2 image. As a result, this research opens new insights into how current very high-resolution, small-scale caribou lichen maps can be used for generating more accurate large-scale caribou lichen maps from high-resolution satellite imagery.
Summary(Plain Language Summary, not published)
Lichen is an important food source for caribou in Canada. Lichen mapping using remote sensing images is a challenging task, however, as lichens generally appear in unevenly distributed, small patches, and could resemble surficial features. Moreover, collecting lichen ground truth data is expensive, which restricts the application of many robust supervised classification models that generally demand a large quantity of labeled data. The goal of this study was to investigate the potential of using a very-high-spatial resolution (1-cm) lichen map of a small sample site (e.g., generated based on a single UAV scene and using field reference data) to train a subsequent classifier to map caribou lichen over a much larger area (~0.04 km2 vs ~195 km2) and a lower spatial resolution image (in this case, a 50-cm WorldView-2 image). We used a Teacher-Student semi-supervised learning approach that trains Teacher and Student networks iteratively on both ground-truthed and not-ground-truthed data. This approach produced lichen maps at the WorldView scale with an ~85% overall accuracy.
GEOSCAN ID329023

 
Date modified: