Automated Distance Estimation for Wildlife Camera Trapping

Abstract

The ongoing biodiversity crysis calls for accurate estimation of animal density and abundance to identify, for example, sources of biodiversity decline and effectiveness of conservation interventions. Camera traps together with abundance estimation methods are often employed for this purpose. The necessary distances between camera and observed animal are traditionally derived in a laborious, fully manual or semi-automatic process. Both approaches require reference image material, which is both difficult to acquire and not available for existing datasets. In this study, we propose a fully automatic approach to estimate camera-to-animal distances, based on monocular depth estimation (MDE), and without the need of reference image material. We leverage stateof-the-art relative MDE and a novel alignment procedure to estimate metric distances. We evaluate the approach on a zoo scenario dataset unseen during training. We achieve a mean absolute distance estimation error of only 0.9864 meters at a precision of 90.3% and recall of 63.8%, while completely eliminating the previously required manual effort for biodiversity researchers. The code will be made available.

A semi‐automated camera trap distance sampling approach for population density estimation

“…The method can be applied to a variety of species and settings, since it does not depend on the size and outline of the animals or the form of the terrain and just requires two reference images per camera trap location. Future advances might omit the need for reference images and fully automate the process (Johanns et al, 2022).…”