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

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:
YOLOv8 Small
MobileNet V3
TensorFlowLite
bird classification
automated sampling
mobile app
Online Access:https://www.mdpi.com/2673-2688/6/3/57
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2673-2688

Similar Items