Metadata augmented deep neural networks for wild animal classification
This incremental improvement addresses wildlife surveillance challenges in suboptimal conditions, potentially reducing reliance on image quality for researchers.
The paper tackles wild animal classification from camera trap imagery by augmenting image data with metadata (temperature, location, time), achieving an accuracy increase from 98.4% to 98.9% on a Norwegian climate dataset and demonstrating high accuracy with metadata-only classification.
Camera trap imagery has become an invaluable asset in contemporary wildlife surveillance, enabling researchers to observe and investigate the behaviors of wild animals. While existing methods rely solely on image data for classification, this may not suffice in cases of suboptimal animal angles, lighting, or image quality. This study introduces a novel approach that enhances wild animal classification by combining specific metadata (temperature, location, time, etc) with image data. Using a dataset focused on the Norwegian climate, our models show an accuracy increase from 98.4% to 98.9% compared to existing methods. Notably, our approach also achieves high accuracy with metadata-only classification, highlighting its potential to reduce reliance on image quality. This work paves the way for integrated systems that advance wildlife classification technology.