Integration of YOLOv8 Small and MobileNet V3 Large for Efficient Bird Detection and Classification on Mobile Devices

Background: Bird species identification and classification are crucial for biodiversity research, conservation initiatives, and ecological monitoring. However, conventional identification techniques used by biologists are time-consuming and susceptible to human error. The integration of deep learnin...

Full description

Saved in:
Bibliographic Details
Main Authors: Axel Frederick Félix-Jiménez, Vania Stephany Sánchez-Lee, Héctor Alejandro Acuña-Cid, Isaul Ibarra-Belmonte, Efraín Arredondo-Morales, Eduardo Ahumada-Tello
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:AI
Subjects:
Online Access:https://www.mdpi.com/2673-2688/6/3/57
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850093644810289152
author Axel Frederick Félix-Jiménez
Vania Stephany Sánchez-Lee
Héctor Alejandro Acuña-Cid
Isaul Ibarra-Belmonte
Efraín Arredondo-Morales
Eduardo Ahumada-Tello
author_facet Axel Frederick Félix-Jiménez
Vania Stephany Sánchez-Lee
Héctor Alejandro Acuña-Cid
Isaul Ibarra-Belmonte
Efraín Arredondo-Morales
Eduardo Ahumada-Tello
author_sort Axel Frederick Félix-Jiménez
collection DOAJ
description Background: Bird species identification and classification are crucial for biodiversity research, conservation initiatives, and ecological monitoring. However, conventional identification techniques used by biologists are time-consuming and susceptible to human error. The integration of deep learning models offers a promising alternative to automate and enhance species recognition processes. Methods: This study explores the use of deep learning for bird species identification in the city of Zacatecas. Specifically, we implement YOLOv8 Small for real-time detection and MobileNet V3 for classification. The models were trained and tested on a dataset comprising five bird species: Vermilion Flycatcher, Pine Flycatcher, Mexican Chickadee, Arizona Woodpecker, and Striped Sparrow. The evaluation metrics included precision, recall, and computational efficiency. Results: The findings demonstrate that both models achieve high accuracy in species identification. YOLOv8 Small excels in real-time detection, making it suitable for dynamic monitoring scenarios, while MobileNet V3 provides a lightweight yet efficient classification solution. These results highlight the potential of artificial intelligence to enhance ornithological research by improving monitoring accuracy and reducing manual identification efforts.
format Article
id doaj-art-eb9761a2aa5343609d58cdd323c0433e
institution DOAJ
issn 2673-2688
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series AI
spelling doaj-art-eb9761a2aa5343609d58cdd323c0433e2025-08-20T02:41:51ZengMDPI AGAI2673-26882025-03-01635710.3390/ai6030057Integration of YOLOv8 Small and MobileNet V3 Large for Efficient Bird Detection and Classification on Mobile DevicesAxel Frederick Félix-Jiménez0Vania Stephany Sánchez-Lee1Héctor Alejandro Acuña-Cid2Isaul Ibarra-Belmonte3Efraín Arredondo-Morales4Eduardo Ahumada-Tello5Instituto Politécnico Nacional, Unidad Profesional Interdisciplinaria de Ingeniería Campus Zacatecas (UPIIZ), Academia de Ciencias de la Computación, Zacatecas 98160, MexicoInstituto Politécnico Nacional, Unidad Profesional Interdisciplinaria de Ingeniería Campus Zacatecas (UPIIZ), Academia de Ciencias de la Computación, Zacatecas 98160, MexicoInstituto Politécnico Nacional, Unidad Profesional Interdisciplinaria de Ingeniería Campus Zacatecas (UPIIZ), Academia de Ciencias de la Computación, Zacatecas 98160, MexicoCentro de Investigación en Matemáticas (CIMAT), Unidad Zacatecas, Departamento de Ingeniería de Software, Zacatecas 98160, MexicoInstituto Politécnico Nacional, Unidad Profesional Interdisciplinaria de Ingeniería Campus Zacatecas (UPIIZ), Academia de Ciencias de la Computación, Zacatecas 98160, MexicoFacultad de Contaduría y Administración, Universidad Autónoma de Baja California, Tijuana 22424, MexicoBackground: Bird species identification and classification are crucial for biodiversity research, conservation initiatives, and ecological monitoring. However, conventional identification techniques used by biologists are time-consuming and susceptible to human error. The integration of deep learning models offers a promising alternative to automate and enhance species recognition processes. Methods: This study explores the use of deep learning for bird species identification in the city of Zacatecas. Specifically, we implement YOLOv8 Small for real-time detection and MobileNet V3 for classification. The models were trained and tested on a dataset comprising five bird species: Vermilion Flycatcher, Pine Flycatcher, Mexican Chickadee, Arizona Woodpecker, and Striped Sparrow. The evaluation metrics included precision, recall, and computational efficiency. Results: The findings demonstrate that both models achieve high accuracy in species identification. YOLOv8 Small excels in real-time detection, making it suitable for dynamic monitoring scenarios, while MobileNet V3 provides a lightweight yet efficient classification solution. These results highlight the potential of artificial intelligence to enhance ornithological research by improving monitoring accuracy and reducing manual identification efforts.https://www.mdpi.com/2673-2688/6/3/57YOLOv8 SmallMobileNet V3TensorFlowLitebird classificationautomated samplingmobile app
spellingShingle Axel Frederick Félix-Jiménez
Vania Stephany Sánchez-Lee
Héctor Alejandro Acuña-Cid
Isaul Ibarra-Belmonte
Efraín Arredondo-Morales
Eduardo Ahumada-Tello
Integration of YOLOv8 Small and MobileNet V3 Large for Efficient Bird Detection and Classification on Mobile Devices
AI
YOLOv8 Small
MobileNet V3
TensorFlowLite
bird classification
automated sampling
mobile app
title Integration of YOLOv8 Small and MobileNet V3 Large for Efficient Bird Detection and Classification on Mobile Devices
title_full Integration of YOLOv8 Small and MobileNet V3 Large for Efficient Bird Detection and Classification on Mobile Devices
title_fullStr Integration of YOLOv8 Small and MobileNet V3 Large for Efficient Bird Detection and Classification on Mobile Devices
title_full_unstemmed Integration of YOLOv8 Small and MobileNet V3 Large for Efficient Bird Detection and Classification on Mobile Devices
title_short Integration of YOLOv8 Small and MobileNet V3 Large for Efficient Bird Detection and Classification on Mobile Devices
title_sort integration of yolov8 small and mobilenet v3 large for efficient bird detection and classification on mobile devices
topic YOLOv8 Small
MobileNet V3
TensorFlowLite
bird classification
automated sampling
mobile app
url https://www.mdpi.com/2673-2688/6/3/57
work_keys_str_mv AT axelfrederickfelixjimenez integrationofyolov8smallandmobilenetv3largeforefficientbirddetectionandclassificationonmobiledevices
AT vaniastephanysanchezlee integrationofyolov8smallandmobilenetv3largeforefficientbirddetectionandclassificationonmobiledevices
AT hectoralejandroacunacid integrationofyolov8smallandmobilenetv3largeforefficientbirddetectionandclassificationonmobiledevices
AT isaulibarrabelmonte integrationofyolov8smallandmobilenetv3largeforefficientbirddetectionandclassificationonmobiledevices
AT efrainarredondomorales integrationofyolov8smallandmobilenetv3largeforefficientbirddetectionandclassificationonmobiledevices
AT eduardoahumadatello integrationofyolov8smallandmobilenetv3largeforefficientbirddetectionandclassificationonmobiledevices