Wildlife surveillance using deep learning methods
Problem
Screening still and video camera surveillance of wild animals for species of interest is laborious and expensive, hindering wildlife conflict management such as bovine tuberculosis control.
Why it matters
Cost-effective monitoring matters for managing Mycobacterium bovis transmission between badgers and cattle.
What the AI did
The authors developed a deep learning approach to automatically identify and isolate species-specific activity, distinguishing badgers from other species (binary) and classifying six animal species, using 8,368 images.
Results
not stated in source (abstract truncated before accuracy figures)
Impact
The work offers an automated screening tool for wildlife surveillance imagery.
Record
| Venue | Ecology and Evolution |
|---|---|
| Published | 2019 |
| Work type | article |
| Authors | Ruilong Chen, Ruth A. Little, Lyudmila S. Mihaylova, Richard John Delahay, Ruth Cox |
| Citations | 90 (OpenAlex, at import time) |
| References | 35 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1002/ece3.5410 |
| Open access | gold |
| Keywords | deep learning, wildlife monitoring, badger, bovine tuberculosis, image classification |
Importance rating
real but narrower advance
Cost-effective wildlife monitoring matters for managing M. bovis transmission between badgers and cattle; abstract calls data volumes enormous but gives no quantified scale.