Efficient Pipeline for Camera Trap Image Review
This addresses a domain-specific challenge for biologists and ecologists using camera traps for wildlife monitoring, but it is incremental as it builds on existing methods.
The paper tackles the problem of applying camera trap species classification models to new geographic regions, where accuracy drops due to background changes and unseen species, by proposing a pipeline that uses a pre-trained animal detector and a small labeled dataset to achieve accurate results efficiently.
Biologists all over the world use camera traps to monitor biodiversity and wildlife population density. The computer vision community has been making strides towards automating the species classification challenge in camera traps, but it has proven difficult to to apply models trained in one region to images collected in different geographic areas. In some cases, accuracy falls off catastrophically in new region, due to both changes in background and the presence of previously-unseen species. We propose a pipeline that takes advantage of a pre-trained general animal detector and a smaller set of labeled images to train a classification model that can efficiently achieve accurate results in a new region.