-
Uddannelse
Find uddannelse
Studievejledning
Kvalitet
- Forskning
-
Samarbejde
Virksomheder
Kommuner og regioner
Gymnasier
Myndigheder
-
Om AU
Organisation
Kontakt
Du er her: AU » Om AU » Organisation
» Kim Bjerge
»
Publikationer
»
A light trap and computer vision system to detect and cla...
Om AU
- Organisation
- Ledelse
- Strategi
- AU i tal
- AU's historie
- Internationalt samarbejde
- Bæredygtighed
- Campus 2.0
- Diversitet og ligestilling
- Ledige stillinger
- Presse
- Kontakt
Kim Bjerge
A light trap and computer vision system to detect and classify live moths(Lepidoptera) using tracking and deep learning
Publikation: Working paper/Preprint › Working paper › Forskning
- Kim Bjerge
- Jakob Bonde Nielsen, Danmark
- Martin Videbæk Sepstrup, Danmark
- Flemming Helsing-Nielsen, Danmark
- Toke Thomas Høye
This paper presents a portable computer vision system, that is able to attract and detect live insects.
More specically, the paper proposes detection and classication of species by recording images of live
moths captured by a light trap. A light trap with multiple illuminations and a camera was designed to
attract and monitor live insects during twilight and night hours. A computer vision algorithm referred to
as Moth Classication and Counting, based on deep learning analysis of the captured images then tracked
and counted the number of insects and identied moth species. This paper presents the design and the
algorithm that were used to determine and identify the moth species. Observations over 48 nights resulted
in the capture of more than 250,000 images with an average of 5,675 images per night. A customized
convolutional neural network was trained on 864 labelled images of live moths, which were divided in to
eight dierent species, achieving a high validation F1-score of 0.96. The algorithm measured an average
classication and tracking F1-score of 0.83 and a tracking detection rate of 0.79. This result was based on
an estimate of 83 individual moths observed during one night with insect activity in 122 minutes collecting
6,000 images. Overall, the proposed computer vision system and algorithm showed promising results in
nondestructive and automatic monitoring of moths as well as classication of species. The system provides
a cost-eective alternative to traditional methods, which require time-consuming manual identication and
typically provides coarse temporal solution to capturing data. In addition, the system avoids depleting
moth populations in the monitoring process, which is a problem in traditional traps that kill individual
moths. As image libraries grow and become more complete, the images captured by the trapping system
can be processed automatically and allow users with limited experience to collect data on insect abundance,
biomass, and diversity.
More specically, the paper proposes detection and classication of species by recording images of live
moths captured by a light trap. A light trap with multiple illuminations and a camera was designed to
attract and monitor live insects during twilight and night hours. A computer vision algorithm referred to
as Moth Classication and Counting, based on deep learning analysis of the captured images then tracked
and counted the number of insects and identied moth species. This paper presents the design and the
algorithm that were used to determine and identify the moth species. Observations over 48 nights resulted
in the capture of more than 250,000 images with an average of 5,675 images per night. A customized
convolutional neural network was trained on 864 labelled images of live moths, which were divided in to
eight dierent species, achieving a high validation F1-score of 0.96. The algorithm measured an average
classication and tracking F1-score of 0.83 and a tracking detection rate of 0.79. This result was based on
an estimate of 83 individual moths observed during one night with insect activity in 122 minutes collecting
6,000 images. Overall, the proposed computer vision system and algorithm showed promising results in
nondestructive and automatic monitoring of moths as well as classication of species. The system provides
a cost-eective alternative to traditional methods, which require time-consuming manual identication and
typically provides coarse temporal solution to capturing data. In addition, the system avoids depleting
moth populations in the monitoring process, which is a problem in traditional traps that kill individual
moths. As image libraries grow and become more complete, the images captured by the trapping system
can be processed automatically and allow users with limited experience to collect data on insect abundance,
biomass, and diversity.
| Originalsprog | Engelsk |
|---|---|
| Status | Udgivet - 20 mar. 2020 |
| Serietitel | Bioarxiv |
|---|
Se relationer på Aarhus Universitet Citationsformater
ID: 185056941