Self-Calibration of UAV Thermal Imagery Using Gradient Descent Algorithm

Abstract

Unmanned aerial vehicle (UAV) thermal imagery offers several advantages for environmental monitoring, as it can provide a low-cost, high-resolution, and flexible solution to measure the temperature of the surface of the land. Limitations related to the maximum load of the drone lead to the use of lightweight uncooled thermal cameras whose internal components are not stabilized to a constant temperature. Such cameras suffer from several unwanted effects that contribute to the increase in temperature measurement error from ±0.5 °C in laboratory conditions to ±5 °C in unstable flight conditions. This article describes a post-processing procedure that reduces the above unwanted effects. It consists of the following steps: (i) devignetting using the single image vignette correction algorithm, (ii) georeferencing using image metadata, scale-invariant feature transform (SIFT) stitching, and gradient descent optimisation, and (iii) inter-image temperature consistency optimisation by minimisation of bias between overlapping thermal images using gradient descent optimisation. The solution was tested in several case studies of river areas, where natural water bodies were used as a reference temperature benchmark. In all tests, the precision of the measurements was increased. The root mean square error (RMSE) on average was reduced by 39.0% and mean of the absolute value of errors (MAE) by 40.5%. The proposed algorithm can be called self-calibrating, as in contrast to other known solutions, it is fully automatic, uses only field data, and does not require any calibration equipment or additional operator effort. A Python implementation of the solution is available on GitHub.