Geographical Transferability of Lulc Image-Based Segmentation Models Using Training Data Automatically Generated From Openstreetmap – Case Study in Portugal

Abstract

Abstract. Synoptic remote sensing systems have been broadly used within supervised classification methods to map land use and land cover (LULC). Such methods rely on high quality sets of training data that are able to characterize the target classes. Often, training data is manually generated, either by field campaigns and/or by photointerpretation of ancillary remote sensing imagery. Several authors already proposed methodologies to attenuate such labour-intensive task of generating training data. One of the preferred datasets that are used as input training data is OpenStreetMap (OSM), which aims at creating a publicly available vector map of the world with the input of volunteers. However, OSM data is spatially heterogenous (e.g., capital cities and highly populated areas often have high degrees of completion while unpopulated regions often have a lower degree of completion), where there are still large areas without OSM coverage. In this paper we present a set of experiments that aim at assessing the geographical transferability of satellite image-based segmentation models trained with OSM derived data. To this end, we chose two locations with different OSM coverage and disparate landscape (metropolitan region vs natural park region, in different landscape units), and assess how these models behave when trained in a region and applied in the other. The results show that the mapping of some classes is improved when considering a model trained in a different location.

MeViT: Medium-Resolution Vision Transformer for Semantic Segmentation on Landsat Satellite Imagery for Agriculture in Thailand

“…Traditionally, human experts' manual interpretation of remote sensing data was time-consuming and laborious. With the advent of deep learning techniques, particularly CNNs, automatic LULC feature extraction has become much faster and more accurate [23][24][25][26] . The automatic identification and mapping of different land use and cover types provide valuable information for various applications 17,[27][28][29][30][31] , including urban planning, agriculture, forestry, disaster management, and environmental monitoring.…”

MeViT: A Medium-Resolution Vision Transformer for Semantic Segmentation on Landsat Satellite Imagery for Agriculture in Thailand

“…Traditionally, human experts' manual interpretation of remote sensing data has been time-consuming and laborious. With deep learning techniques, particularly convolutional neural networks (CNNs), automatic LULC feature extraction has become much faster and more accurate [7][8][9][10]. The automatic identification and mapping of different land use and cover types provide valuable information for various applications [1,[11][12][13][14][15], including urban planning, agriculture, forestry, disaster management, and environmental monitoring.…”