Automated morphometric modelling of an endangered freshwater cetacean from unscaled UAV imagery using an internal scaling framework

Abstract

With the rapid advancement of drone technology, aerial photogrammetry has been increasingly applied to morphometric research, particularly for endangered species, owing to its fully non-invasive nature. Photogrammetry-derived morphometric models (e.g., three-dimensional reconstructions) provide critical insights into individual health conditions and population demographic characteristics. Conventional aerial photogrammetry relies on external scale calibration to convert image measurements into real-world dimensions, which remains a major challenge for free-ranging animals because accurate scaling requires prior knowledge of image acquisition parameters or external references that are often unavailable under field conditions. Using the endangered Yangtze finless porpoise ( Neophocaena asiaeorientalis asiaeorientalis ) as a model species, we demonstrated that the allometric development of blowhole length (distance from the tip of the rostrum to the posterior margin of the blowhole) results in significant age-specific differences in the blowhole-length-to-body-length ratio, providing an internal scaling metric that is independent of image scale. The long-term accumulation of age and body length measurements has generated a rich dataset that enables the establishment of accurate age–length relationships, while a recent rescue operation provided a unique opportunity to obtain direct and accurate morphometric measurements for validating the internal scaling framework and the novel Segmented Weighted Integration Model (SWIM). We further developed a computer program that automates pixel extraction, metric conversion, model implementation, parameter calculation, and data tabulation. Significant differences in the blowhole-length-to-body-length ratio were observed among calves (n = 11), juveniles (n = 36), and adults (n = 35) (ANOVA, P < 0.01), with all pairwise comparisons remaining significant (calves vs. juveniles, P < 0.001; calves vs. adults, P < 0.001; juveniles vs. adults, P < 0.01). The model demonstrated high accuracy in estimating body length from unscaled images without prior knowledge of flight altitude or camera focal length, achieving a mean absolute error of 6.69 cm and a mean absolute percentage error of 5.02% across 62 test images. Our study presents an automated and accurate approach for estimating body length from a single unscaled dorsal-view drone image using an internal scaling framework and the SWIM, providing a practical tool for rapid morphometric assessment of marine mammals.