Unifying data for fine-grained visual species classification

TL;DR

This paper discusses unifying diverse wildlife image data and presents a deep learning model trained on millions of images to improve automated species classification, aiding conservation efforts.

Contribution

It introduces a data unification effort for wildlife images and a deep neural network model for fine-grained species classification.

Findings

Model trained on 2.9 million images across 465 species

Aims to reduce manual classification workload

Supports near real-time conservation analysis

Abstract

Wildlife monitoring is crucial to nature conservation and has been done by manual observations from motion-triggered camera traps deployed in the field. Widespread adoption of such in-situ sensors has resulted in unprecedented data volumes being collected over the last decade. A significant challenge exists to process and reliably identify what is in these images efficiently. Advances in computer vision are poised to provide effective solutions with custom AI models built to automatically identify images of interest and label the species in them. Here we outline the data unification effort for the Wildlife Insights platform from various conservation partners, and the challenges involved. Then we present an initial deep convolutional neural network model, trained on 2.9M images across 465 fine-grained species, with a goal to reduce the load on human experts to classify species in images manually. The long-term goal is to enable scientists to make conservation recommendations from near real-time analysis of species abundance and population health.