@inproceedings{8e8394337132469bb6ccdf4921288d55,
title = "Real-time GeoAI for High-resolution Mapping and Segmentation of Arctic Permafrost Features The case of ice-wedge polygons",
abstract = "This paper introduces a real-time GeoAI workflow for large-scale image analysis and the segmentation of Arctic permafrost features at a fine-granularity. Very high-resolution (0.5m) commercial imagery is used in this analysis. To achieve real-time prediction, our workflow employs a lightweight, deep learning-based instance segmentation model, SparseInst, which introduces and uses Instance Activation Maps to accurately locate the position of objects within the image scene. Experimental results show that the model can achieve better accuracy of prediction at a much faster inference speed than the popular Mask-RCNN model.",
keywords = "GeoAI, arctic, artificial intelligence, instance segmentation, permafrost",
author = "Wenwen Li and Hsu, {Chia Yu} and Sizhe Wang and Chandi Witharana and Anna Liljedahl",
note = "Publisher Copyright: {\textcopyright} 2022 ACM.; 5th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2022 ; Conference date: 01-11-2022",
year = "2022",
month = nov,
day = "1",
doi = "10.1145/3557918.3565869",
language = "English (US)",
series = "Proceedings of the 5th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2022",
publisher = "Association for Computing Machinery, Inc",
pages = "62--65",
editor = "Bruno Martins and Dalton Lunga and Song Gao and Shawn Newsam and Lexie Yang and Xueqing Deng and Gengchen Mai",
booktitle = "Proceedings of the 5th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2022",
}