LGCVMLApr 23, 2019

Spatio-temporal crop classification of low-resolution satellite imagery with capsule layers and distributed attention

arXiv:1904.10130v12 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of monitoring global development goals like climate-smart agriculture and sustainable land management by enabling accurate crop classification without expensive high-resolution imagery, though it is incremental in method.

The paper tackled the problem of land use classification using low-resolution satellite imagery by developing a model combining capsule layers and LSTM with distributed attention, achieving state-of-the-art accuracy for temporal crop type classification at 30x30m resolution with Sentinel 2 imagery.

Land use classification of low resolution spatial imagery is one of the most extensively researched fields in remote sensing. Despite significant advancements in satellite technology, high resolution imagery lacks global coverage and can be prohibitively expensive to procure for extended time periods. Accurately classifying land use change without high resolution imagery offers the potential to monitor vital aspects of global development agenda including climate smart agriculture, drought resistant crops, and sustainable land management. Utilizing a combination of capsule layers and long-short term memory layers with distributed attention, the present paper achieves state-of-the-art accuracy on temporal crop type classification at a 30x30m resolution with Sentinel 2 imagery.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes