A Smart Trap for Counting Olive Moths Based on the Internet of Things and Deep Learning

被引：1

作者：

Mdhaffar, Afef ^{[1
,3
]}

Zalila, Bechir ^{[1
,3
]}

Moalla, Racem ^{[3
]}

Kharrat, Ayoub ^{[3
]}

Rebai, Omar ^{[3
]}

Hsairi, Mohamed Melek ^{[3
]}

Sallemi, Ahmed ^{[3
]}

Kobbi, Hsouna ^{[3
]}

Kolsi, Amel ^{[2
]}

Chatti, Dorsaf ^{[2
]}

Jmaiel, Mohamed ^{[1
,3
]}

Freisleben, Bernd ^{[4
]}

机构：

[1] Univ Sfax, ReDCAD Lab, ENIS, BP 1173, Sfax, Tunisia

[2] Olive Inst Sfax, Sfax, Tunisia

[3] Digital Res Ctr Sfax, Sfax, Tunisia

[4] Univ Marburg, Dept Math & Comp Sci, Marburg, Germany

来源：

2022 IEEE/ACS 19TH INTERNATIONAL CONFERENCE ON COMPUTER SYSTEMS AND APPLICATIONS (AICCSA) | 2022年

关键词：

IoT; AI; smart trap; olive moth (Prays oleae); insect detection; deep learning; PraysDB dataset;

D O I：

10.1109/AICCSA56895.2022.10017905

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present a novel smart trap for counting olive moths using Internet of Things principles and deep learning algorithms. The smart trap takes a picture of the captured insects once per day and processes it using a deep convolutional neural network to detect "Prays oleae" insects and count their number. Then, the results are transferred via a wireless connection to a backend cloud server. The proposed smart trap is designed to reduce power consumption as much as possible. Two deep neural network models (i.e., YOLO V5 and YOLO V7) are employed to detect and count Prays oleae insects, using our newly created Prays oleae dataset, PraysDB. Our experimental results demonstrate the detection quality, energy efficiency, and computational performance of our smart trap.

引用

页数：8

共 15 条

[1] Bochkovskiy A., 2020, ARXIV 200410934
[2] Le AD, 2022, Arxiv, DOI [arXiv:2112.13341, 10.48550/arxiv.2112.1334137]
[3] InsectCV: A system for insect detection in the lab from trap images
De Cesaro Junior, Telmo
Rieder, Rafael
Di Domenico, Jessica Regina
Lau, Douglas
[J]. ECOLOGICAL INFORMATICS, 2022, 67
[4] DIRT Dataset, DIRT ONL DET
[5] github, YOLO V7
[6] github, YOLO V6
[7] A Review of Yolo Algorithm Developments
Jiang, Peiyuan
Ergu, Daji
Liu, Fangyao
Cai, Ying
Ma, Bo
[J]. 8TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND QUANTITATIVE MANAGEMENT (ITQM 2020 & 2021): DEVELOPING GLOBAL DIGITAL ECONOMY AFTER COVID-19, 2022, 199 : 1066 - 1073
[8] DIRT: The Dacus Image Recognition Toolkit
Kalamatianos, Romanos
Karydis, Ioannis
Doukakis, Dimitris
Avlonitis, Markos
[J]. JOURNAL OF IMAGING, 2018, 4 (11)
[9] YOLO-Based Deep Learning Framework for Olive Fruit Fly Detection and Counting
Mamdouh, Nariman
Khattab, Ahmed
[J]. IEEE ACCESS, 2021, 9 : 84252 - 84262
[10] Mating Disruption of the Olive Moth Prays oleae (Bernard) in Olive Groves Using Aerosol Dispensers
Ortiz, Antonio
Porras, Andres
Marti, Jordi
Tudela, Antonio
Rodriguez-Gonzalez, Alvaro
Sambado, Paolo
[J]. INSECTS, 2021, 12 (12)

← 1 2 →