e-obs Stories & Publications
Discover a World of Wildlife Science
With over two decades of unwavering commitment to serving the needs of tagged animals and our valued customers, we’ve forged deep connections in the world of wildlife research. Our relentless passion drives us to continually elevate our products, expanding our portfolio to benefit you.
Proven Impact
Our products have played a pivotal role in countless studies, spanning a diverse array of remarkable creatures, from coconut crabs (Birgus latro) to majestic red kites (Milvus milvus) and agile cheetahs (Acinonyx jubatus). The e-obs community, fueled by our technology, consistently pushes the boundaries of wildlife science, resulting in a wealth of publications that testify to the excellence of our materials and the exceptional work of our users.
Basso, Enzo; Beirne, Christopher; Petri, Tobias; Goldhahn, Cody; Luthy, Kyle; Crowe, William; Zinke, Marcus; Wicks, Sarah; Tubelli, Eduardo; Chulla, Diego Rollim; Berger, Matthias; Whitworth, Andrew
In: Animal Biotelemetry, 2026, ISSN: 2050-3385.
Abstract | Links | BibTeX | Tags: accelerometer, accelerometry, animal-borne video, behavioral classification, drop-off system, ground truthing, ground-truth validation, king vulture, Sarcoramphus papa, Vulture
@article{basso_ground-truth_2026,
title = {Ground-truth validation of behavioral classifications from accelerometer data using an integrated GPS-accelerometer-camera device: application to an elusive scavenger},
author = {Enzo Basso and Christopher Beirne and Tobias Petri and Cody Goldhahn and Kyle Luthy and William Crowe and Marcus Zinke and Sarah Wicks and Eduardo Tubelli and Diego Rollim Chulla and Matthias Berger and Andrew Whitworth},
url = {https://link.springer.com/10.1186/s40317-026-00494-w},
doi = {10.1186/s40317-026-00494-w},
issn = {2050-3385},
year = {2026},
date = {2026-09-01},
urldate = {2026-09-15},
journal = {Animal Biotelemetry},
abstract = {Background Animal-borne cameras integrated with multi-sensor devices offer a powerful tool for hypothesisdriven research. Video recordings enable ground-truth validation of behavioral modes inferred from triaxial accelerometer data in wild animals. However, retrieving video data can be challenging due to battery limitations and the lack of remote download stations. We tested a GPS\textendashaccelerometer device integrated with a customized camera and a harness drop-off system on two adult King Vultures (Sarcoramphus papa), an elusive Neotropical scavenger. Video recordings from animal-borne cameras were used to establish behavioral reference annotations, which were temporally aligned with accelerometer data and compared against the output of a Self-Organizing Map algorithm to validate behavioral classification performance. Model performance was evaluated using precision, recall, and F1-score metrics.
Results Prototypes were successfully deployed, yielding a total of 764 video files and 2 h 16 min of footage for ground-truth validation. Five to six behavioral modes were identified per individual and matched with accelerometer data. Resting was the most common behavior (59.2\textendash69.9% of time), followed by flight modes such as soaring\textendashgliding (textasciitilde 19%) and flapping (textasciitilde 3%), while preening accounted for 7.6\textendash17.3% of activity and feeding was rare (1.36%, observed in one individual only). Model performance varied across behaviors and individuals. Resting showed high classification performance (F1-score: 0.72\textendash0.89), as did soaring\textendashgliding (F1-score: 0.73\textendash0.94). Flapping achieved moderate performance (F1-score: 0.68\textendash0.76), while preening showed lower classification performance (F1-score: 0.37\textendash0.38). Feeding was poorly classified (F1-score: 0.26), reflecting higher behavioral variability and class imbalance.
Conclusion Animal-borne video provides behavioral reference data for evaluating accelerometer-based behavioral classification models. We evaluated the performance of our prototype, demonstrating its utility for recording behavior in elusive species and offering a solution where direct validation of acceleration data is difficult. We recognize several aspects that should be improved in future designs, including prototype weight, shape, and},
keywords = {accelerometer, accelerometry, animal-borne video, behavioral classification, drop-off system, ground truthing, ground-truth validation, king vulture, Sarcoramphus papa, Vulture},
pubstate = {published},
tppubtype = {article}
}
Results Prototypes were successfully deployed, yielding a total of 764 video files and 2 h 16 min of footage for ground-truth validation. Five to six behavioral modes were identified per individual and matched with accelerometer data. Resting was the most common behavior (59.2–69.9% of time), followed by flight modes such as soaring–gliding (textasciitilde 19%) and flapping (textasciitilde 3%), while preening accounted for 7.6–17.3% of activity and feeding was rare (1.36%, observed in one individual only). Model performance varied across behaviors and individuals. Resting showed high classification performance (F1-score: 0.72–0.89), as did soaring–gliding (F1-score: 0.73–0.94). Flapping achieved moderate performance (F1-score: 0.68–0.76), while preening showed lower classification performance (F1-score: 0.37–0.38). Feeding was poorly classified (F1-score: 0.26), reflecting higher behavioral variability and class imbalance.
Conclusion Animal-borne video provides behavioral reference data for evaluating accelerometer-based behavioral classification models. We evaluated the performance of our prototype, demonstrating its utility for recording behavior in elusive species and offering a solution where direct validation of acceleration data is difficult. We recognize several aspects that should be improved in future designs, including prototype weight, shape, and