Abstract
Lichen 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.
Highlights
The rescaling was based on a majorityvoting approach; that is, if more than 50% of the pixels of the UAV-derived lichen map within a pixel footprint of WorldView image were classified as lichen, we considered that pixel as lichen
The best result of training the Teacher-Student framework was achieved after three iterations namely that the Student network was used as a Teacher in two iterations
The most obvious performance improvement can be seen over the road pixels and some tree types that were differentiated more accurately from lichen patches as the network evolved
Summary
The main driver of this population decline is still ambiguous, most factors thought to be contributing are directly or indirectly related to human activities [2,3], such as land-cover changes that can affect resource availability for caribou [4] and can cause them to change their distribution, migration, and timing patterns when foraging for food [5]. Lichen is an important source of food for caribou especially during winters [6,7]. Based on our quantitative the SSL-based WorldView lichen. 48.68% assessment, Overfitted model map had an OA of 85.28% and F1-score of 84.38%. 1275lichen unless than the rate of misclassification of lichen pixels as772 background
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.