Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-21542
Publication type: Article in scientific journal
Type of review: Peer review (publication)
Title: Deep learning for automated detection of Drosophila suzukii : potential for UAV‐based monitoring
Authors: Roosjen, Peter PJ
Kellenberger, Benjamin
Kooistra, Lammert
Green, David R
Fahrentrapp, Johannes
et. al: No
DOI: 10.1002/ps.5845
10.21256/zhaw-21542
Published in: Pest Management Science
Volume(Issue): 76
Issue: 9
Page(s): 2994
Pages to: 3002
Issue Date: 4-Apr-2020
Publisher / Ed. Institution: Wiley
ISSN: 1526-498X
1526-4998
Language: English
Subjects: UAV; Pest monitoring; Integrated pest management; IPM
Subject (DDC): 006: Special computer methods
632: Plant diseases, pests
Abstract: BACKGROUND: The fruit fly Drosophila suzukii, or spotted wing drosophila (SWD), is a serious pest worldwide, attacking many soft-skinned fruits. An efficient monitoring system that identifies and counts SWD in crops and their surroundings is therefore essential for integrated pest management (IPM) strategies. Existing methods, such as catching flies in liquid bait traps and counting them manually, are costly, time-consuming and labour-intensive. To overcome these limitations, we studied insect trap monitoring using image-based object detection with deep learning. RESULTS: Based on an image database with 4753 annotated SWDflies, we trained a ResNet-18-based deep convolutional neural network to detect and count SWD, including sex prediction and discrimination. The results show that SWD can be detected with an area under the precision recall curve (AUC) of 0.506 (female) and 0.603 (male) in digital images taken from a static position. For images collected using an unmanned aerial vehicle (UAV), the algorithm detected SWD individuals with an AUC of 0.086 (female) and 0.284 (male). The lower AUC for the aerial imagery was due to lower image quality caused by stabilisation manoeuvres of the UAV during image collection. CONCLUSION: Our results indicate that it is possible to monitor SWD using deep learning and object detection. Moreover, the results demonstrate the potential of UAVs to monitor insect traps, which could be valuable in the development of autonomous insect monitoring systems and IPM.
URI: https://digitalcollection.zhaw.ch/handle/11475/21542
Fulltext version: Published version
License (according to publishing contract): CC BY 4.0: Attribution 4.0 International
Departement: Life Sciences and Facility Management
Organisational Unit: Institute of Natural Resource Sciences (IUNR)
Published as part of the ZHAW project: Automated Airborne Pest Monitoring AAPM of Drosophila suzukii in Crops and Natural Habitats
Appears in collections:Publikationen Life Sciences und Facility Management

Files in This Item:
File Description SizeFormat 
2020_Roosjen_etal_Deep-learning-for-automated-detection-of-Drosophila-suzukii.pdf7.61 MBAdobe PDFThumbnail
View/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.