Abstract
Supervised classification is the commonly used method for extracting ground information from images. However, for supervised classification, the selection and labelling of training samples is an expensive and time-consuming task. Recently, automatic information indexes have achieved satisfactory results for indicating different land-cover classes, which makes it possible to develop an automatic method for labelling the training samples instead of manual interpretation. In this paper, we propose a method for the automatic selection and labelling of training samples for high-resolution image classification. In this way, the initial candidate training samples can be provided by the information indexes and open-source geographical information system (GIS) data, referring to the representative land-cover classes: buildings, roads, soil, water, shadow, and vegetation. Several operations are then applied to refine the initial samples, including removing overlaps, removing borders, and semantic constraints. The proposed sampling method is evaluated on a series of high-resolution remote sensing images over urban areas, and is compared to classification with manually labeled training samples. It is found that the proposed method is able to provide and label a large number of reliable samples, and can achieve satisfactory results for different classifiers. In addition, our experiments show that active learning can further enhance the classification performance, as active learning is used to choose the most informative samples from the automatically labeled samples.
Highlights
Classification is one of the most vital phases for remote sensing image interpretation, and the classification model learned from the training samples should be extended and transferred in the whole image
support vector machine (SVM) has proven effective in hyperspectral image classification [9], high spatial resolution image classification [10], and multi-classifier ensemble strategies [11,12]
We propose to automatically select and label the training samples on the basis of a set of information sources, e.g., the morphological building/shadow index (MBI, Morphological Shadow Index (MSI)) [24,25], the normalized difference water/vegetation index (NDWI, Normalized Difference Vegetation Index (NDVI)) [26,27], the HSV color space, and open-source geographical information system (GIS) data, e.g., road lines from OpenStreetMap (OSM) [28]
Summary
Classification is one of the most vital phases for remote sensing image interpretation, and the classification model learned from the training samples should be extended and transferred in the whole image. To the best of our knowledge, there have been few papers discussing machine learning methods that can automatically label training samples from remote sensing images. In this context, we propose to automatically select and label the training samples on the basis of a set of information sources, e.g., the morphological building/shadow index (MBI, MSI) [24,25], the normalized difference water/vegetation index (NDWI, NDVI) [26,27], the HSV color space, and open-source geographical information system (GIS) data, e.g., road lines from OpenStreetMap (OSM) [28].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
