Spatial Morphing Kernel Regression For Feature Interpolation
This work addresses the challenge of dense mapping from sparse social media data for applications like land use mapping, representing an incremental improvement in interpolation methods for geographic knowledge discovery.
The paper tackles the problem of generating dense maps from sparse and unevenly distributed geotagged social media data by spatially interpolating high-dimensional features, showing that an interpolate-then-classify framework can produce dense maps but requires careful choice of interpolation method, with spatial morphing kernel regression improving results.
In recent years, geotagged social media has become popular as a novel source for geographic knowledge discovery. Ground-level images and videos provide a different perspective than overhead imagery and can be applied to a range of applications such as land use mapping, activity detection, pollution mapping, etc. The sparse and uneven distribution of this data presents a problem, however, for generating dense maps. We therefore investigate the problem of spatially interpolating the high-dimensional features extracted from sparse social media to enable dense labeling using standard classifiers. Further, we show how prior knowledge about region boundaries can be used to improve the interpolation through spatial morphing kernel regression. We show that an interpolate-then-classify framework can produce dense maps from sparse observations but that care must be taken in choosing the interpolation method. We also show that the spatial morphing kernel improves the results.