Nambiar KG, Morgenshtern V, Hochreuther P, Seehaus T, Braun M (2022)
Publication Type: Journal article
Publication year: 2022
Book Volume: 14
Pages Range: 1825
Issue: 8
DOI: 10.3390/rs14081825
Screening clouds, shadows, and snow is a critical pre-processing step in many remote-sensing data processing pipelines that operate on satellite image data from polar and high mountain regions. We observe that the results of the state-of-the-art Fmask algorithm are not very accurate in polar and high mountain regions. Given the unavailability of large, labeled Sentinel-2 training datasets, we present a multi-stage self-training approach that trains a model to perform semantic segmentation on Sentinel-2 L1C images using the noisy Fmask labels for training and a small human-labeled dataset for validation. At each stage of the proposed iterative framework, we use a larger network architecture in comparison to the previous stage and train a new model. The trained model at each stage is then used to generate new training labels for a bigger dataset, which are used for training the model in the next stage. We select the best model during training in each stage by evaluating the multi-class segmentation metric, mean Intersection over Union (mIoU), on the small human-labeled validation dataset. This effectively helps to correct the noisy labels. Our model achieved an overall accuracy of 93% compared to the Fmask 4 and Sen2Cor 2.8, which achieved 75% and 76%, respectively. We believe our approach can also be adapted for other remote-sensing applications for training deep-learning models with imprecise labels.
APA:
Nambiar, K.G., Morgenshtern, V., Hochreuther, P., Seehaus, T., & Braun, M. (2022). A Self-Trained Model for Cloud, Shadow and Snow Detection in Sentinel-2 Images of Snow- and Ice-Covered Regions. Remote Sensing, 14, 1825. https://dx.doi.org/10.3390/rs14081825
MLA:
Nambiar, Kamal Gopikrishnan, et al. "A Self-Trained Model for Cloud, Shadow and Snow Detection in Sentinel-2 Images of Snow- and Ice-Covered Regions." Remote Sensing 14 (2022): 1825.
BibTeX: Download