Estimating Wingbeat Frequency of Hummingbirds using a No-labeling Learning Computer Vision Approach.

Wingbeat frequency estimation is an important aspect for the study of avian flight, energetics, and behavioral patterns, among others. Hummingbirds, in particular, are ideal subjects to test a method for this estimation due to their fast wing motions and unique aerodynamics, which results from their ecological diversification, adaptation to high-altitude environments, and sexually selected displays. Traditionally, wingbeat frequency measurements have been done via "manual" image/sound processing. In this study, we present an automated method to detect, track, classify, and monitor hummingbirds in high-speed video footage, accurately estimating their wingbeat frequency using computer vision techniques and signal analysis. Our approach utilizes a zero-shot learning algorithm that eliminates the need for labeling during training. Results demonstrate that our method can produce automated wingbeat frequency estimations with minimal supervision, closely matching those performed by trained human observers. This comparison indicates that our method can, in some scenarios, achieve low or zero error compared to a human, making it a valuable tool for flight analysis. Automating video analysis can assist wingbeat frequency estimation by reducing processing time and, thus, lowering barriers to analyze biological data on fields such as aerodynamics, foraging behavior, and signaling.