Crop Classification Maps Filtration Based on Deep Learning Methods

Abstract

In this paper we proposed filtration methods for land cover and land use classification maps, that obtained based on high resolution satellite images. The main idea is to adapt and utilize state-of-the-art deep learning fully convolutional and U-net architectures, that previously have been used for image segmentation, for classification map filtration task and to compare them with traditional rule-based approach. The most complicated tasks in the filtering such maps are to preserve edges, boundaries between different fields and automatically take into account not only single object or its neighbors, but also consider whole surrounded situation. The proposed U-net architecture allows us to overcome these issues and to provide more accurate and precise filtration in terms of accuracies per class. Also, McNemar statistical test has been conducted to prove the statistically significant gain of utilizing proposed filtration methodology compare to initial classification map. In addition, it shows advantages comparing to rule-based method in successfully dealing with big objects of noise in large fields and at the same time prevent significant changes in small farmer fields that grouped near villages or towns.