Seg2Map: New Tools for ML-based Segmentation of Geospatial Imagery
This proposal would fund the development of Seg2Map, a new open-source, browser-accessible software deployed on the cloud that will apply Machine Learning to imagery and image time-series, to make highly customizable to study Earth’s changing surface for a range of scientific purposes.
Seg2Map will be an open-source, browser-accessible software deployed on the cloud that will apply Machine Learning to imagery and image time-series, to make (and re-make) highly customizable maps of Land Use and Land Cover (LULC) and associated uncertainties, in order to study Earth’s changing surface for a range of scientific purposes. It will consist of three main elements: 1) a web interface for downloading of user-defined Earth Observation (ostensibly, satellite) imagery in user-defined regions of interest, or for uploading and reprojecting existing geospatial imagery; 2) tools for application of advanced pixelwise classification (or ‘image segmentation’) based on state-of-the-art Machine Learning algorithms; and 3) post-processing tools for quality assurance and uncertainty quantification.
This proposal would fund the development of Seg2Map, a new open-source, browser-accessible software deployed on the cloud that will apply Machine Learning to imagery and image time-series, to make highly customizable to study Earth’s changing surface for a range of scientific purposes.
Seg2Map will be an open-source, browser-accessible software deployed on the cloud that will apply Machine Learning to imagery and image time-series, to make (and re-make) highly customizable maps of Land Use and Land Cover (LULC) and associated uncertainties, in order to study Earth’s changing surface for a range of scientific purposes. It will consist of three main elements: 1) a web interface for downloading of user-defined Earth Observation (ostensibly, satellite) imagery in user-defined regions of interest, or for uploading and reprojecting existing geospatial imagery; 2) tools for application of advanced pixelwise classification (or ‘image segmentation’) based on state-of-the-art Machine Learning algorithms; and 3) post-processing tools for quality assurance and uncertainty quantification.