Results of the 1st Asynchronous CASTLE Challenge at the Joint Egocentric Vision Workshop in Conjunction with CVPR 2026
报告总结了2026年CVPR联合自我中心视觉研讨会上首次异步CASTLE挑战赛的贡献和结果，探讨了异步数据处理方法。
0 citationsRead paper
Selected work
Representative Papers
Habitat and Land Cover Change Detection in Alpine Protected Areas: A Comparison of AI Architectures
Manual habitat mapping in alpine ecosystems is costly, and conventional methods underperform in scenarios involving ambiguous boundaries and class imbalance. Method: This study pioneers the application of geospatial foundation models (Prithvi-EO-2.0 and Clay v1.0) to multi-temporal land cover change detection in Alpine protected areas. We systematically compare post-classification change detection versus direct change detection paradigms, integrating RGB, near-infrared (NIR), LiDAR, and topographic data; notably, we innovatively leverage LiDAR to enhance semantic segmentation. Results: Clay v1.0 achieves 51% overall accuracy in multi-class change detection—outperforming U-Net by 10 percentage points—and attains an IoU of 0.53 and binary classification accuracy of 67% under the direct change detection framework. It demonstrates markedly superior cross-year generalization compared to supervised models. Moreover, LiDAR integration boosts segmentation accuracy from 30% to 50%, confirming its critical role in improving fine-grained habitat delineation.
0 citationsRead paper
Recent publications
Latest Papers
Results of the 1st Asynchronous CASTLE Challenge at the Joint Egocentric Vision Workshop in Conjunction with CVPR 2026
报告总结了2026年CVPR联合自我中心视觉研讨会上首次异步CASTLE挑战赛的贡献和结果，探讨了异步数据处理方法。
0 citationsRead paper
Habitat and Land Cover Change Detection in Alpine Protected Areas: A Comparison of AI Architectures
Manual habitat mapping in alpine ecosystems is costly, and conventional methods underperform in scenarios involving ambiguous boundaries and class imbalance. Method: This study pioneers the application of geospatial foundation models (Prithvi-EO-2.0 and Clay v1.0) to multi-temporal land cover change detection in Alpine protected areas. We systematically compare post-classification change detection versus direct change detection paradigms, integrating RGB, near-infrared (NIR), LiDAR, and topographic data; notably, we innovatively leverage LiDAR to enhance semantic segmentation. Results: Clay v1.0 achieves 51% overall accuracy in multi-class change detection—outperforming U-Net by 10 percentage points—and attains an IoU of 0.53 and binary classification accuracy of 67% under the direct change detection framework. It demonstrates markedly superior cross-year generalization compared to supervised models. Moreover, LiDAR integration boosts segmentation accuracy from 30% to 50%, confirming its critical role in improving fine-grained habitat delineation.
0 citationsRead paper