Metadata augmented deep neural networks for wild animal classification

Aslak Tøn, Ammar Ahmed, Ali Shariq Imran, Mohib Ullah, R. Muhammad Atif Azad
9/7/2024
cs.CV

No official code found. Best implementation: ammarlodhi255/metadata-augmented-neural-networks-for-wild-animal-classification (2 stars, MIT, last commit 2024-08-26).

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.

View on arXivView PDF

Code Implementations(1)

ammarlodhi255/metadata-augmented-neural-networks-for-wild-animal-classificationCommunity100%
MIT

This repository contains the implementation code for the paper "Metadata Augmented Neural Networks For Wild Animal Classification": https://www.sciencedirect.com/science/article/pii/S1574954124003479.

20Python, JavaScriptAug 25, 20242 years agoMIT
deep-learningfusion-techniquesmetadatametadata-fusionmulti-modal+3 more

Similar Papers

Reevaluating Automated Wildlife Species Detection: A Reproducibility Study on a Custom Image Dataset

88% match2025

Evaluating Deep Learning Models for African Wildlife Image Classification: From DenseNet to Vision Transformers

88% match2025

Transfer Learning for Wildlife Classification: Evaluating YOLOv8 against DenseNet, ResNet, and VGGNet on a Custom Dataset

87% match2024

Towards Context-Rich Automated Biodiversity Assessments: Deriving AI-Powered Insights from Camera Trap Data

86% match2024

WildIng: A Wildlife Image Invariant Representation Model for Geographical Domain Shift

86% match1 repo32026

Evaluation of deep learning architectures for wildlife object detection: A comparative study of ResNet and Inception

86% match2025

Cite this paper

@article{tn2024metadata,
  title  = {Metadata augmented deep neural networks for wild animal classification},
  author = {Aslak Tøn and Ammar Ahmed and Ali Shariq Imran and Mohib Ullah and R. Muhammad Atif Azad},
  year   = {2024},
  eprint = {2409.04825},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.04825v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.04825.svg)](https://codeofpaper.com/paper/2409.04825)

Discussion