A Tracking‐By‐Detection Framework to Automatically Count Rare and Elusive Megafauna in Aerial Video Surveys
Abstract
Video surveys from drones or planes equipped with cameras have become invaluable tools for monitoring populations of rare and elusive megafauna over increasingly large spatial scales. To analyze hours of such video surveys, automated species detection approaches based on deep learning are now widely used, but simply tallying detections on the successive frames of videos leads to double counting of individuals, significantly biasing population size estimates. Here, we leverage a multiple object tracking approach that links detections across video frames to derive counts of unique individuals. Our tracking‐by‐detection framework integrates the full pipeline from aerial video surveys to automated individual count and estimation of minimum population abundance. Applied to aerial video surveys of dugongs ( Dugong dugon ) on the west coast of New Caledonia in winter, our framework automatically counted individuals with a slight negative bias of −5.7% (−15 individuals over a total of 265 ground‐truth individuals) compared to a baseline method relying on the sum of detections that led to a 48 times overestimation. Our tracking‐by‐detection framework directly estimated the number of unique individuals per flight, leading to a mean seasonal index of abundance of 42 individuals (±28 SD) in the surveyed area. Overall, 35 individuals were missed across flights, representing 13.2% of all ground‐truth individuals. Among missed individuals, two‐thirds were calves superposed to their mothers, stressing the challenge of occlusion when counting group‐living animals. Despite being applied to entire videos with very low prevalence of dugongs, our framework generated just 8% of false positives (20 instances) across all flights, mostly due to misidentifications with other species. Illustrated through the case of dugong, our tracking‐by‐detection framework more generally provides a scalable method to support digital population surveys, benefitting long‐term monitoring and conservation programs of vulnerable megafauna.
Related
- Vision In SyndrOmic Neurodevelopmental disorders-15q (VISiON-15q) study: eye tracking to supplement clinical examination for detection of cerebral/cortical visual impairment in children with Angelman and Duplication of 15q Syndromes
- Ecosystem engineer restores trophic interactions: beavers alter landscape of risks and resources for megafauna
- Beyond snapshots: A dynamic framework for continuous motor unit tracking to enhance neurophysiological assessments
- Fast, automated, real‐time 3D passive balloon catheter tracking during MRI ‐guided cardiac catheterization using orthogonal projection imaging and real‐time image‐based catheter detection
- Optimizing Marine eDNA Protocols for Rare Megafauna: A Case Study on Dugongs in the Western Indian Ocean
BibTeX
@article{mannocci2026trackingbydetection,
title = {{A Tracking‐By‐Detection Framework to Automatically Count Rare and Elusive Megafauna in Aerial Video Surveys}},
author = {Laura Mannocci and Auguste Verdier and Louis Bézard and Valentine Fleuré and Gerard Subsol and Marc Chaumont and David Mouillot},
journal = {Remote Sensing in Ecology and Conservation},
year = {2026},
month = aug,
doi = {10.1002/rse2.70097},
url = {https://hal.science/hal-05801656v1},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - A Tracking‐By‐Detection Framework to Automatically Count Rare and Elusive Megafauna in Aerial Video Surveys
AU - Laura Mannocci
AU - Auguste Verdier
AU - Louis Bézard
AU - Valentine Fleuré
AU - Gerard Subsol
AU - Marc Chaumont
AU - David Mouillot
PY - 2026
DA - 2026/08/12
JO - Remote Sensing in Ecology and Conservation
DO - 10.1002/rse2.70097
UR - https://hal.science/hal-05801656v1
AB - Video surveys from drones or planes equipped with cameras have become invaluable tools for monitoring populations of rare and elusive megafauna over increasingly large spatial scales. To analyze hours of such video surveys, automated species detection approaches based on deep learning are now widely used, but simply tallying detections on the successive frames of videos leads to double counting of individuals, significantly biasing population size estimates. Here, we leverage a multiple object tracking approach that links detections across video frames to derive counts of unique individuals. Our tracking‐by‐detection framework integrates the full pipeline from aerial video surveys to automated individual count and estimation of minimum population abundance. Applied to aerial video surveys of dugongs ( Dugong dugon ) on the west coast of New Caledonia in winter, our framework automatically counted individuals with a slight negative bias of −5.7% (−15 individuals over a total of 265 ground‐truth individuals) compared to a baseline method relying on the sum of detections that led to a 48 times overestimation. Our tracking‐by‐detection framework directly estimated the number of unique individuals per flight, leading to a mean seasonal index of abundance of 42 individuals (±28 SD) in the surveyed area. Overall, 35 individuals were missed across flights, representing 13.2% of all ground‐truth individuals. Among missed individuals, two‐thirds were calves superposed to their mothers, stressing the challenge of occlusion when counting group‐living animals. Despite being applied to entire videos with very low prevalence of dugongs, our framework generated just 8% of false positives (20 instances) across all flights, mostly due to misidentifications with other species. Illustrated through the case of dugong, our tracking‐by‐detection framework more generally provides a scalable method to support digital population surveys, benefitting long‐term monitoring and conservation programs of vulnerable megafauna.
SN - 2056-3485
ER -