Metadata Augmented Deep Neural Networks for Wild Animal Classification  

Aslak Tøn (Corresponding / Lead Author), Ammar Ahmed, Ali Shariq Imran* (Corresponding / Lead Author), Mohib Ullah, R. Muhammad Atif Azad

*Corresponding author for this work

    Research output: Contribution to journalArticlepeer-review

    Abstract

    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.
    Original languageEnglish
    Article number102805
    JournalEcological Informatics
    Volume83
    DOIs
    Publication statusPublished (VoR) - 2 Sept 2024

    Fingerprint

    Dive into the research topics of 'Metadata Augmented Deep Neural Networks for Wild Animal Classification  '. Together they form a unique fingerprint.

    Cite this