UAV-Multispectral Sensed Data Band Co-Registration Framework

Abstract

Precision farming has greatly benefited from new technologies over the years. The use of multispectral and hyperspectral sensors coupled to Unmanned Aerial Vehicles (UAV) has enabled farms to monitor crops, improve the use of resources and reduce costs. Despite being widely used, multispectral images present a natural misalignment among the various spectra due to the use of different sensors. The variation of the analyzed spectrum also leads to a loss of characteristics among the bands which hinders the feature detection process among the bands, which makes the alignment process complex. In this work, we propose a new framework for the band co-registration process based on two premises: i) the natural misalignment is an attribute of the camera, so it does not change during the acquisition process; ii) the speed of displacement of the UAV when compared to the speed between the acquisition of the first to the last band, is not sufficient to create significant distortions. We compared our results with the ground-truth generated by a specialist and with other methods present in the literature. The proposed framework had an average back-projection (BP) error of 0.425 pixels, this result being 335% better than the evaluated frameworks.