AntPi: A Raspberry Pi based edge–cloud system for real-time ant species detection using YOLO

Ant detection is essential for ecological research, offering insights into biodiversity, habitat health, and environmental change. Traditional detection techniques rely on manual sampling methods, which are labor-intensive and time-consuming. Recent advances in autonomous, vision based systems show...

Full description

Saved in:
Bibliographic Details
Main Authors: Lorenzo Palazzetti, Daniele Giannetti, Antonio Verolino, Donato A. Grasso, Cristina M. Pinotti, Francesco Betti Sorbelli
Format: Article
Language:English
Published: Elsevier 2025-11-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954125003929
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849228392892727296
author Lorenzo Palazzetti
Daniele Giannetti
Antonio Verolino
Donato A. Grasso
Cristina M. Pinotti
Francesco Betti Sorbelli
author_facet Lorenzo Palazzetti
Daniele Giannetti
Antonio Verolino
Donato A. Grasso
Cristina M. Pinotti
Francesco Betti Sorbelli
author_sort Lorenzo Palazzetti
collection DOAJ
description Ant detection is essential for ecological research, offering insights into biodiversity, habitat health, and environmental change. Traditional detection techniques rely on manual sampling methods, which are labor-intensive and time-consuming. Recent advances in autonomous, vision based systems show promise for insect monitoring, yet no dedicated, field ready solution exists for ant identification. In this work, we present AntPi, a deep learning based system for real-time detection and classification on a Linux development board. To the best of our knowledge, the system is trained on the first dedicated dataset for arboricolous ants, comprising five species and one morphotype, sourced from citizen science contributions and direct field captures. Our approach employs the “You Only Look Once” (YOLO) framework for efficient object detection, augmented with environmental sensors to enable correlation between climatic variables and ant activity. To evaluate performance and robustness, we compare AntPi with an alternative configuration, including controlled experiments using background-only images with artificial ant-like noise, and introduce a novel robustness indicator to assess reliability under realistic conditions. Experimental results demonstrate strong detection performance and confirm the feasibility of automated, in-field ant monitoring.
format Article
id doaj-art-bd11ea4bf7eb4d6e90c78421e6a98d59
institution Kabale University
issn 1574-9541
language English
publishDate 2025-11-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-bd11ea4bf7eb4d6e90c78421e6a98d592025-08-23T04:47:48ZengElsevierEcological Informatics1574-95412025-11-019110338310.1016/j.ecoinf.2025.103383AntPi: A Raspberry Pi based edge–cloud system for real-time ant species detection using YOLOLorenzo Palazzetti0Daniele Giannetti1Antonio Verolino2Donato A. Grasso3Cristina M. Pinotti4Francesco Betti Sorbelli5Department of Computer Science and Mathematics, University of Perugia, Italy; Corresponding author.Department of Chemistry, Life Sciences and Environmental Sustainability, University of Parma, ItalyDepartment of Chemistry, Life Sciences and Environmental Sustainability, University of Parma, ItalyDepartment of Chemistry, Life Sciences and Environmental Sustainability, University of Parma, ItalyDepartment of Computer Science and Mathematics, University of Perugia, ItalyDepartment of Computer Science and Mathematics, University of Perugia, ItalyAnt detection is essential for ecological research, offering insights into biodiversity, habitat health, and environmental change. Traditional detection techniques rely on manual sampling methods, which are labor-intensive and time-consuming. Recent advances in autonomous, vision based systems show promise for insect monitoring, yet no dedicated, field ready solution exists for ant identification. In this work, we present AntPi, a deep learning based system for real-time detection and classification on a Linux development board. To the best of our knowledge, the system is trained on the first dedicated dataset for arboricolous ants, comprising five species and one morphotype, sourced from citizen science contributions and direct field captures. Our approach employs the “You Only Look Once” (YOLO) framework for efficient object detection, augmented with environmental sensors to enable correlation between climatic variables and ant activity. To evaluate performance and robustness, we compare AntPi with an alternative configuration, including controlled experiments using background-only images with artificial ant-like noise, and introduce a novel robustness indicator to assess reliability under realistic conditions. Experimental results demonstrate strong detection performance and confirm the feasibility of automated, in-field ant monitoring.http://www.sciencedirect.com/science/article/pii/S1574954125003929IoTAnt detectionComputer visionTechnological transferEdge computing
spellingShingle Lorenzo Palazzetti
Daniele Giannetti
Antonio Verolino
Donato A. Grasso
Cristina M. Pinotti
Francesco Betti Sorbelli
AntPi: A Raspberry Pi based edge–cloud system for real-time ant species detection using YOLO
Ecological Informatics
IoT
Ant detection
Computer vision
Technological transfer
Edge computing
title AntPi: A Raspberry Pi based edge–cloud system for real-time ant species detection using YOLO
title_full AntPi: A Raspberry Pi based edge–cloud system for real-time ant species detection using YOLO
title_fullStr AntPi: A Raspberry Pi based edge–cloud system for real-time ant species detection using YOLO
title_full_unstemmed AntPi: A Raspberry Pi based edge–cloud system for real-time ant species detection using YOLO
title_short AntPi: A Raspberry Pi based edge–cloud system for real-time ant species detection using YOLO
title_sort antpi a raspberry pi based edge cloud system for real time ant species detection using yolo
topic IoT
Ant detection
Computer vision
Technological transfer
Edge computing
url http://www.sciencedirect.com/science/article/pii/S1574954125003929
work_keys_str_mv AT lorenzopalazzetti antpiaraspberrypibasededgecloudsystemforrealtimeantspeciesdetectionusingyolo
AT danielegiannetti antpiaraspberrypibasededgecloudsystemforrealtimeantspeciesdetectionusingyolo
AT antonioverolino antpiaraspberrypibasededgecloudsystemforrealtimeantspeciesdetectionusingyolo
AT donatoagrasso antpiaraspberrypibasededgecloudsystemforrealtimeantspeciesdetectionusingyolo
AT cristinampinotti antpiaraspberrypibasededgecloudsystemforrealtimeantspeciesdetectionusingyolo
AT francescobettisorbelli antpiaraspberrypibasededgecloudsystemforrealtimeantspeciesdetectionusingyolo