Publication Type
Conference Paper
Book Title
IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
Publication Date
Page Numbers
619 to 622
Issue
IGARSS 202
Publisher Location
New Jersey, United States of America
Conference Name
International Geoscience and Remote Sensing Symposium (IGARSS)
Conference Location
Kuala Lumpur, Malaysia
Conference Sponsor
IEEE
Conference Date
-
Abstract
We propose a weakly-supervised, multitask framework for training a convolutional neural network to solve the problem of cloud shadow mitigation given only cloud and shadow masks as labels. The network minimizes the Wasserstein distance between shadows and their proximal sunlit neighborhoods, generating a supervisory signal directly from within the input image. We extract further utility from the shadow mask through multitask learning by introducing an auxiliary task of shadow segmentation. Our approach is advantageous since it performs mitigation in an end-to-end framework which requires only a shadowed image for inference. We apply this process to the Landsat 8 OLI SPARCS validation data set and demonstrate plausible results.
