Multi-temporal Calving Front Segmentation
This work addresses the need for continuous monitoring of marine-terminating glaciers to understand mass and dynamic changes, representing an incremental improvement in domain-specific deep learning methods.
The paper tackled the problem of accurately segmenting calving fronts in satellite imagery, which is challenging due to seasonal conditions like ice melange or snow-covered surfaces, and achieved a new state-of-the-art performance with a Mean Distance Error of 184.4 m and a mean Intersection over Union of 83.6 on the CaFFe benchmark dataset.
The calving fronts of marine-terminating glaciers undergo constant changes. These changes significantly affect the glacier's mass and dynamics, demanding continuous monitoring. To address this need, deep learning models were developed that can automatically delineate the calving front in Synthetic Aperture Radar imagery. However, these models often struggle to correctly classify areas affected by seasonal conditions such as ice melange or snow-covered surfaces. To address this issue, we propose to process multiple frames from a satellite image time series of the same glacier in parallel and exchange temporal information between the corresponding feature maps to stabilize each prediction. We integrate our approach into the current state-of-the-art architecture Tyrion and accomplish a new state-of-the-art performance on the CaFFe benchmark dataset. In particular, we achieve a Mean Distance Error of 184.4 m and a mean Intersection over Union of 83.6.