Correction of systematic image misalignment in direct georeferencing of UAV multispectral imagery

Mosaicking of Unmanned Aerial Vehicles (UAV) imagery over featureless water bodies has been known to be challenging, and poses a significant impediment to water monitoring applications. Techniques such as Structure-from-motion typically fail under such conditions due to the lack of distinctive features in the scene, and direct georeferencing is currently the only practical solution, albeit lower georeferencing accuracy is expected. However, hardware issues, particularly the typical time delay between the GPS unit and the image capture, can lead to systematic image misalignment and further reducing the accuracy. The systematic image misalignment arises as the recording of the geographical coordinates by the GPS unit may not precisely correspond to the exact moment of image exposure, and the image exposure may not always occur at the mid-exposure time. Hardware solutions can mitigate this issue but require technical expertise and resources. Alternatively, software solutions can address the problem without necessitating any hardware modifications. This study introduces an open-source solution for the correction of the systematic image alignment by accounting for the time delay and distance discrepancy between the measurements of the GPS coordinates and the image capture. The method was validated with field UAV surveys conducted in this study under various flight configurations (different flight altitudes and overlap ratios), and effective image alignment was obtained using the proposed open-source solution which reduced the georeferencing error by around 67.7%. Specifically, a georeferencing error of RMSE = 1.409 m and (Formula presented.) = 0.6356 m was achieved without the use of any ground control points (GCPs). Finally, as demonstrated in this study, low flight altitudes (e.g. 15 m) should be discouraged for such conditions as georeferencing errors could amplify due to the limited accuracy of the GPS, resulting in visual artefacts.