⚙
AI-generated deep summary
by claude@2026-07, 2026-07-14
· read from full text
ⓘ
The paper presents an end-to-end workflow for near real-time wildlife population monitoring using uncrewed aircraft systems (drones) and computer vision to identify and count individual wading birds in the Everglades, with imagery collected weekly and processed into orthomosaics for rapid conversion into monitoring data. Using an automated pipeline built around Snakemake, orthomosaics are analyzed with a RetinaNet-50 object detector to produce accurate object detection, species classification, and both total and species-level counts for five of six target species, with poor performance for Snowy Egrets due to limited training labels and visual similarity to White Ibis. The authors report that automating post-survey processing makes population data available in under one week from survey date. The paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.
Abstract
Wildlife population monitoring over large geographic areas is increasingly feasible due to developments in aerial survey methods coupled with the use of computer vision models for identifying and classifying individual organisms. However, aerial surveys still occur infrequently, and there are often long delays between the acquisition of airborne imagery and its conversion into population monitoring data. Near real-time monitoring is increasingly important for active management decisions and ecological forecasting. Accomplishing this over large scales requires a combination of airborne imagery, computer vision models to process imagery into information on individual organisms, and automated workflows to ensure that imagery is quickly processed into data following acquisition. Here we present our end-to-end workflow for conducting near real-time monitoring of wading birds in the Everglades, Florida, USA. Imagery is acquired as frequently as weekly using uncrewed aircraft systems (aka drones), processed into orthomosaics (using Agisoft metashape), converted into individual level species data using a Retinanet-50 object detector, post-processed, archived, and presented on a web-based visualization platform (using Shiny). The main components of the workflow are automated using Snakemake. The underlying computer vision model provides accurate object detection, species classification, and both total and species-level counts for five out of six target species (White Ibis, Great Egret, Great Blue Heron, Wood Stork, and Roseate Spoonbill). The model performed poorly for Snowy Egrets due to the small number of labels and difficulty distinguishing them from White Ibis (the most abundant species). By automating the post-survey processing, data on the populations of these species is available in near real-time (< 1 week from the date of the survey) providing information at the time-scales needed for ecological forecasting and active management.
Full text
2,411 characters
· extracted from
oa-doi-fallback
· click to expand
Abstract
Wildlife population monitoring over large geographic areas is increasingly feasible due to developments in aerial survey methods coupled with the use of computer vision models for identifying and classifying individual organisms. However, aerial surveys still occur infrequently, and there are often long delays between the acquisition of airborne imagery and its conversion into population monitoring data. Near real-time monitoring is increasingly important for active management decisions and ecological forecasting. Accomplishing this over large scales requires a combination of airborne imagery, computer vision models to process imagery into information on individual organisms, and automated workflows to ensure that imagery is quickly processed into data following acquisition. Here we present our end-to-end workflow for conducting near real-time monitoring of wading birds in the Everglades, Florida, USA. Imagery is acquired as frequently as weekly using uncrewed aircraft systems (aka drones), processed into orthomosaics (using Agisoft metashape), converted into individual level species data using a Retinanet-50 object detector, post-processed, archived, and presented on a web-based visualization platform (using Shiny). The main components of the workflow are automated using Snakemake. The underlying computer vision model provides accurate object detection, species classification, and both total and species-level counts for five out of six target species (White Ibis, Great Egret, Great Blue Heron, Wood Stork, and Roseate Spoonbill). The model performed poorly for Snowy Egrets due to the small number of labels and difficulty distinguishing them from White Ibis (the most abundant species). By automating the post-survey processing, data on the populations of these species is available in near real-time (< 1 week from the date of the survey) providing information at the time-scales needed for ecological forecasting and active management.
Competing Interest Statement
Andrew Ortega is now a consultant at Aries Geospatial, which conducts which conducts UAS flights and data analysis related that overlap with the area of research described in the paper.
Footnotes
1. Clarify and provide additional methodological details 2. Improvements to the clarity of the language 3. Added additional citations 4. Added discussion of areas for application outside of the focal study system
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.