Skip to main content

Global Partitioning Elevation Normalization Applied to Building Footprint Prediction

by Alexander Fafard, Jan Van Aardt, Mark A Coletti, David L Page
Publication Type
Journal Name
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Publication Date
Page Numbers
1 to 11

Understanding and exploiting topographical data via standard machine learning techniques is challenging, mainly due to the large dynamic range of values present in elevation data and the lack of direct relationships between anthropogenic phenomena and topography, when considering topographic-geology couplings, for instance. Here we consider the first hurdle, dynamic range, in an effort to apply convolutional neural network (CNN) approaches for prediction of human activity. CNNs for learning 3D elevation data rely on data normalization approaches, which only consider locally available points, thereby discarding contextual information and eliminating global contrast cues. We present a fully invertible and data-driven global partitioning elevation normalization (GPEN) pre-processing technique, which is intended to ameliorate the impact of limited data dynamic range. Global elevation populations are derived and used to formulate a distribution, which is used to adopt a partitioning scheme to remap all values according to global occurrence frequency, while preserving partition contrast. Using USGS 3D Elevation Project and Microsoft building footprint data, we conduct a binary classification experiment predicting building footprint presence from elevation data, with and without a global remapping using the SegNet convolutional encoder-decoder model. The results of the experiment show more rapid model convergence, reduced regionalization errors, and enhanced classification metrics when compared to standard normalization preprocessing techniques. GPEN demonstrates performance over 10% higher than the next best conventional preprocessing method, with a mean overall accuracy of 94.76%. GPEN may show promise as an alternative normalization for deep learning with topological data.