Human Assisted Artificial Intelligence Based Technique to Create Natural Features for OpenStreetMap
This work addresses the challenge of mapping natural features in OpenStreetMap for users and communities relying on open geospatial data, but it appears incremental as it builds on existing interactive machine learning methods.
The paper tackles the problem of creating natural features for OpenStreetMap by proposing an AI-based technique that uses freely available satellite images and integrates human editors as initiators and validators, resulting in an interactive machine learning approach that efficiently extracts classes from spectral signatures and converts them to editable features.
In this work, we propose an AI-based technique using freely available satellite images like Landsat and Sentinel to create natural features over OSM in congruence with human editors acting as initiators and validators. The method is based on Interactive Machine Learning technique where human inputs are coupled with the machine to solve complex problems efficiently as compare to pure autonomous process. We use a bottom-up approach where a machine learning (ML) pipeline in loop with editors is used to extract classes using spectral signatures of images and later convert them to editable features to create natural features.