Bayesian aggregation improves traditional single image crop classification approaches

Autor:	Matvienko, Ivan, Gasanov, Mikhail, Petrovskaia, Anna, Jana, Raghavendra Belur, Pukalchik, Maria, Oseledets, Ivan
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning Electrical Engineering and Systems Science - Image and Video Processing
Druh dokumentu:	Working Paper
Popis:	Machine learning (ML) methods and neural networks (NN) are widely implemented for crop types recognition and classification based on satellite images. However, most of these studies use several multi-temporal images which could be inapplicable for cloudy regions. We present a comparison between the classical ML approaches and U-Net NN for classifying crops with a single satellite image. The results show the advantages of using field-wise classification over pixel-wise approach. We first used a Bayesian aggregation for field-wise classification and improved on 1.5% results between majority voting aggregation. The best result for single satellite image crop classification is achieved for gradient boosting with an overall accuracy of 77.4% and macro F1-score 0.66. Comment: Paper presented at the ICLR 2020 Workshop on Computer Vision for Agriculture (CV4A)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2004.03468 Zobrazit plný text záznamu View this record from Arxiv