Bayesian aggregation improves traditional single image crop classification approaches

04/07/2020
by   Ivan Matvienko, et al.
2

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 aggregation. The best result for single satellite image crop classification is achieved for gradient boosting with an overall accuracy of 77.4 F1-score 0.66.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset