Interactive tool improves volcanic plume image segmentation accuracy
GuidedSAM-Plume: An Expert-Guided Segmentation Framework for Volcanic Plumes
Computer Vision and Pattern Recognition
Summary
Measuring features of volcanic smoke and clouds in pictures is hard because there aren't many good automatic tools to do it. This paper shows a new method called GuidedSAM-Plume that helps experts mark these plumes in images more accurately by giving simple hints to a powerful AI model. The new method works much better than fully automatic ones without needing extra training and keeps the important measurements reliable. The authors also created a better dataset with expert guidance that can be used widely by volcanologists and beyond.
What this means in practice
- •For volcanology teams: Use the framework to produce accurate plume shape measurements from images with minimal expert input, improving environmental monitoring of volcanic activity.
- •For environmental monitoring groups: Apply the tool to segment complex, diffuse atmospheric phenomena beyond volcanic plumes, aiding broader environmental science research.
Authors
Taddeo D'Adamo, Simon Thivet, Catherine Pothier, Riccardo Simionato, Allan Fries, Jonathan Lemus, Costanza Bonadonna, Laure Tougne Rodet, Bertrand Kerautret
Abstract
Quantitative analysis of environmental phenomena increasingly relies on image-based measurements. In volcanology, the geometric characterization of volcanic plumes and clouds from RGB images remains hindered by the scarcity of dedicated segmentation solutions and partially handcrafted annotations remain widely prevalent. We present GuidedSAM-Plume, an open-source expert-guided framework tailored for the interactive segmentation of volcanic plumes and clouds. It leverages the zero-shot, spatial prompt-based capabilities of SAM2. The framework was thoroughly validated on a challenging dataset through dedicated segmentation metrics and field-relevant volcanological descriptors. From minimal user inputs, it is able to significantly increase performance compared to fully automatic dedicated solutions while preserving the reliability of derived volcanological parameters. The absence of retraining requirements lowers adoption barriers within the volcanological community, and the framework's demonstrated suitability for complex, diffuse plume-shaped phenomena extends its applicability to broader environmental science domains. The re-annotated dataset, produced under the guidance of expert volcanologists within the proposed framework, ultimately yields a more standardized release. The framework and accompanying dataset are made available at https://github.com/tad-damo/GuidedSAM-Plume.