Annotated UAS imagery of waterbirds in New Mexico
Abstract
We conducted aerial imaging surveys of waterbirds at wildlife management areas in the Middle Rio Grande Valley of New Mexico between 2018 and 2023 using two unoccupied aerial systems: a DJI Mavic Pro 2 (rotary wing) and a Wingtra One Gen II (fixed wing). The DJI imagery was annotated by volunteers on the citizen science Zooniverse web platform between 2021 - 2023. The Wingtra imagery was annotated by the research team in 2024. Broad taxonomic groupings (duck, goose, crane) were used to classify waterbird species. These annotated images were used to train and evaluate convolutional neural networks to detect and classify waterbirds, with the Wingtra imagery solely serving as a test dataset. Further details on data collection, curation, and analysis can be found in the publications in "Related Works" below.
Fields of Study & Subjects
Advanced Neural Network Applications
Remote-Sensing Image Classification
Smart Agriculture and AI
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 20 January 2026
- Language
- EN
- Document type
- Dataset