Manipulating UAV Imagery for Satellite Model Training, Calibration and Testing

TL;DR

This paper introduces a multi-temporal UAV imagery dataset, artificially degraded to satellite quality, enabling improved land use and livestock monitoring through better model calibration and testing.

Contribution

It provides a new high-resolution UAV dataset with ground truth annotations, degraded to satellite quality, for multi-temporal analysis in agricultural remote sensing.

Findings

Created a multi-temporal UAV dataset aligned with satellite imagery.

Developed an empirical blurring metric for realistic data degradation.

Manually annotated cattle labels for ground truthing.

Abstract

Modern livestock farming is increasingly data driven and frequently relies on efficient remote sensing to gather data over wide areas. High resolution satellite imagery is one such data source, which is becoming more accessible for farmers as coverage increases and cost falls. Such images can be used to detect and track animals, monitor pasture changes, and understand land use. Many of the data driven models being applied to these tasks require ground truthing at resolutions higher than satellites can provide. Simultaneously, there is a lack of available aerial imagery focused on farmland changes that occur over days or weeks, such as herd movement. With this goal in mind, we present a new multi-temporal dataset of high resolution UAV imagery which is artificially degraded to match satellite data quality. An empirical blurring metric is used to calibrate the degradation process against actual satellite imagery of the area. UAV surveys were flown repeatedly over several weeks, for specific farm locations. This 5cm/pixel data is sufficiently high resolution to accurately ground truth cattle locations, and other factors such as grass cover. From 33 wide area UAV surveys, 1869 patches were extracted and artificially degraded using an accurate satellite optical model to simulate satellite data. Geographic patches from multiple time periods are aligned and presented as sets, providing a multi-temporal dataset that can be used for detecting changes on farms. The geo-referenced images and 27,853 manually annotated cattle labels are made publicly available.