Metadata Augmented Deep Neural Networks for Wild Animal Classification

Tøn, Aslak and Ahmed, Ammar and Imran, Ali Shariq and Ullah, Mohib and Azad, R. Muhammad Atif (2024) Metadata Augmented Deep Neural Networks for Wild Animal Classification. Ecological Informatics, 83. ISSN 1574-9541

[thumbnail of 1-s2.0-S1574954124003479-main.pdf]
Preview
Text
1-s2.0-S1574954124003479-main.pdf - Published Version
Available under License Creative Commons Attribution.

Download (6MB)

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.

Item Type: Article
Identification Number: 10.1016/j.ecoinf.2024.102805
Dates:
Date
Event
28 August 2024
Accepted
2 September 2024
Published Online
Uncontrolled Keywords: Wild animal detection, Wild animal classification, deep learning data fusion
Subjects: CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science
Divisions: Faculty of Computing, Engineering and the Built Environment > College of Computing
Depositing User: Gemma Tonks
Date Deposited: 17 Sep 2024 10:50
Last Modified: 17 Sep 2024 10:50
URI: https://www.open-access.bcu.ac.uk/id/eprint/15850

Actions (login required)

View Item View Item

Research

In this section...