DEEP LEARNING FOR REMOTE SENSING IMAGE CLASSIFICATION FOR AGRICULTURE APPLICATIONS

• Published in: International archives of the photogrammetry, remote sensing and spatial information sciences. Vol. XLIV-M-2-2020; pp. 51 - 54
• Main Authors: Hashemi-Beni, L., Gebrehiwot, A.
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Gottingen Copernicus GmbH 2020; Copernicus Publications
• Subjects: Agricultural research; Agriculture; Artificial neural networks; Carrots; Classification; Deep learning; Image classification; Machine learning; Model accuracy; Remote sensing; Training; Weeds
• ISSN: 2194-9034; 1682-1750; 2194-9034
• DOI: 10.5194/isprs-archives-XLIV-M-2-2020-51-2020

This research examines the ability of deep learning methods for remote sensing image classification for agriculture applications. U-net and convolutional neural networks are fine-tuned, utilized and tested for crop/weed classification. The dataset for this study includes 60 top-down images of an organic carrots field, which was collected by an autonomous vehicle and labeled by experts. FCN-8s model achieved 75.1% accuracy on detecting weeds compared to 66.72% of U-net using 60 training images. However, the U-net model performed better on detecting crops which is 60.48% compared to 47.86% of FCN-8s.