Land Cover Segmentation with Sparse Annotations from Sentinel-2 Imagery
This addresses the problem of generating accurate land cover maps for environmental analysis and disaster management, but it appears incremental as it builds on existing semantic segmentation and domain adaptation approaches.
The paper tackles land cover segmentation with sparse annotations from Sentinel-2 imagery by introducing SPADA, a framework that uses domain adaptation techniques, and it outperforms state-of-the-art methods with a mean IoU of 42.86 and F1 score of 67.93 on benchmark datasets.
Land cover (LC) segmentation plays a critical role in various applications, including environmental analysis and natural disaster management. However, generating accurate LC maps is a complex and time-consuming task that requires the expertise of multiple annotators and regular updates to account for environmental changes. In this work, we introduce SPADA, a framework for fuel map delineation that addresses the challenges associated with LC segmentation using sparse annotations and domain adaptation techniques for semantic segmentation. Performance evaluations using reliable ground truths, such as LUCAS and Urban Atlas, demonstrate the technique's effectiveness. SPADA outperforms state-of-the-art semantic segmentation approaches as well as third-party products, achieving a mean Intersection over Union (IoU) score of 42.86 and an F1 score of 67.93 on Urban Atlas and LUCAS, respectively.