Aarhus University Seal / Aarhus Universitets segl

An automated light trap to monitor moths (Lepidoptera) using computer vision-based tracking and deep learning

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review

Standard

An automated light trap to monitor moths (Lepidoptera) using computer vision-based tracking and deep learning. / Bjerge, Kim; Nielsen, Jakob Bonde; Sepstrup, Martin Videbæk; Helsing-Nielsen, Flemming; Høye, Toke Thomas.

I: Sensors (Switzerland), Bind 21, Nr. 2, 343, 01.2021.

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review

Harvard

APA

CBE

MLA

Vancouver

Author

Bjerge, Kim ; Nielsen, Jakob Bonde ; Sepstrup, Martin Videbæk ; Helsing-Nielsen, Flemming ; Høye, Toke Thomas. / An automated light trap to monitor moths (Lepidoptera) using computer vision-based tracking and deep learning. I: Sensors (Switzerland). 2021 ; Bind 21, Nr. 2.

Bibtex

@article{3575fb66a34f4efcac847caa86527280,
title = "An automated light trap to monitor moths (Lepidoptera) using computer vision-based tracking and deep learning",
abstract = "Insect monitoring methods are typically very time-consuming and involve substantial investment in species identification following manual trapping in the field. Insect traps are often only serviced weekly, resulting in low temporal resolution of the monitoring data, which hampers the ecological interpretation. This paper presents a portable computer vision system capable of attracting and detecting live insects. More specifically, the paper proposes detection and classification of species by recording images of live individuals attracted to a light trap. An Automated Moth Trap (AMT) with multiple light sources and a camera was designed to attract and monitor live insects during twilight and night hours. A computer vision algorithm referred to as Moth Classification and Counting (MCC), based on deep learning analysis of the captured images, tracked and counted the number of insects and identified moth species. Observations over 48 nights resulted in the capture of more than 250,000 images with an average of 5675 images per night. A customized convolutional neural network was trained on 2000 labeled images of live moths represented by eight different classes, achieving a high validation F1-score of 0.93. The algorithm measured an average classification and tracking F1-score of 0.71 and a tracking detection rate of 0.79. Overall, the proposed computer vision system and algorithm showed promising results as a low-cost solution for non-destructive and automatic monitoring of moths.",
keywords = "Biodiversity, CNN, Computer vision, Deep learning, Insects, Light trap, Moth, Tracking",
author = "Kim Bjerge and Nielsen, {Jakob Bonde} and Sepstrup, {Martin Videb{\ae}k} and Flemming Helsing-Nielsen and H{\o}ye, {Toke Thomas}",
note = "Funding Information: Funding: This research was funded by Danish 15. Juni Fonden grant number 2019-N-23. Publisher Copyright: {\textcopyright} 2021 by the authors. Li-censee MDPI, Basel, Switzerland. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.",
year = "2021",
month = jan,
doi = "10.3390/s21020343",
language = "English",
volume = "21",
journal = "Sensors",
issn = "1424-8220",
publisher = "M D P I AG",
number = "2",

}

RIS

TY - JOUR

T1 - An automated light trap to monitor moths (Lepidoptera) using computer vision-based tracking and deep learning

AU - Bjerge, Kim

AU - Nielsen, Jakob Bonde

AU - Sepstrup, Martin Videbæk

AU - Helsing-Nielsen, Flemming

AU - Høye, Toke Thomas

N1 - Funding Information: Funding: This research was funded by Danish 15. Juni Fonden grant number 2019-N-23. Publisher Copyright: © 2021 by the authors. Li-censee MDPI, Basel, Switzerland. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.

PY - 2021/1

Y1 - 2021/1

N2 - Insect monitoring methods are typically very time-consuming and involve substantial investment in species identification following manual trapping in the field. Insect traps are often only serviced weekly, resulting in low temporal resolution of the monitoring data, which hampers the ecological interpretation. This paper presents a portable computer vision system capable of attracting and detecting live insects. More specifically, the paper proposes detection and classification of species by recording images of live individuals attracted to a light trap. An Automated Moth Trap (AMT) with multiple light sources and a camera was designed to attract and monitor live insects during twilight and night hours. A computer vision algorithm referred to as Moth Classification and Counting (MCC), based on deep learning analysis of the captured images, tracked and counted the number of insects and identified moth species. Observations over 48 nights resulted in the capture of more than 250,000 images with an average of 5675 images per night. A customized convolutional neural network was trained on 2000 labeled images of live moths represented by eight different classes, achieving a high validation F1-score of 0.93. The algorithm measured an average classification and tracking F1-score of 0.71 and a tracking detection rate of 0.79. Overall, the proposed computer vision system and algorithm showed promising results as a low-cost solution for non-destructive and automatic monitoring of moths.

AB - Insect monitoring methods are typically very time-consuming and involve substantial investment in species identification following manual trapping in the field. Insect traps are often only serviced weekly, resulting in low temporal resolution of the monitoring data, which hampers the ecological interpretation. This paper presents a portable computer vision system capable of attracting and detecting live insects. More specifically, the paper proposes detection and classification of species by recording images of live individuals attracted to a light trap. An Automated Moth Trap (AMT) with multiple light sources and a camera was designed to attract and monitor live insects during twilight and night hours. A computer vision algorithm referred to as Moth Classification and Counting (MCC), based on deep learning analysis of the captured images, tracked and counted the number of insects and identified moth species. Observations over 48 nights resulted in the capture of more than 250,000 images with an average of 5675 images per night. A customized convolutional neural network was trained on 2000 labeled images of live moths represented by eight different classes, achieving a high validation F1-score of 0.93. The algorithm measured an average classification and tracking F1-score of 0.71 and a tracking detection rate of 0.79. Overall, the proposed computer vision system and algorithm showed promising results as a low-cost solution for non-destructive and automatic monitoring of moths.

KW - Biodiversity

KW - CNN

KW - Computer vision

KW - Deep learning

KW - Insects

KW - Light trap

KW - Moth

KW - Tracking

UR - http://www.scopus.com/inward/record.url?scp=85099088874&partnerID=8YFLogxK

U2 - 10.3390/s21020343

DO - 10.3390/s21020343

M3 - Journal article

C2 - 33419136

AN - SCOPUS:85099088874

VL - 21

JO - Sensors

JF - Sensors

SN - 1424-8220

IS - 2

M1 - 343

ER -