Spatio-temporal crop classification of low-resolution satellite imagery with capsule layers and distributed attention
Published in
arXiv.org(2019)External Links:
TL
TL;DR
Using 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.
Abstract
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.
References10 items
1
Capsule Networks for Hyperspectral Image Classification
2
Attention-Mechanism-Containing Neural Networks for High-Resolution Remote Sensing Image Classification
3
Hyperspectral Image Classification with Capsule Network Using Limited Training Samples
4
Identifying Aggression and Toxicity in Comments using Capsule Network
5