Bedoukian   RussellIPM   RussellIPM   Piezoelectric Micro-Sprayer


Home
Animal Taxa
Plant Taxa
Semiochemicals
Floral Compounds
Semiochemical Detail
Semiochemicals & Taxa
Synthesis
Control
Invasive spp.
References

Abstract

Guide

Alphascents
Pherobio
InsectScience
E-Econex
Counterpart-Semiochemicals
Print
Email to a Friend
Kindly Donate for The Pherobase

« Previous AbstractLevels and profiles of persistent organic pollutants in resident and migratory birds from an urbanized coastal region of South Korea    Next AbstractEffect of Fermentation Temperature on the Volatile Composition of Kimchi »

Insects


Title:Automatic Pest Counting from Pheromone Trap Images Using Deep Learning Object Detectors for Matsucoccus thunbergianae Monitoring
Author(s):Hong SJ; Nam I; Kim SY; Kim E; Lee CH; Ahn S; Park IK; Kim G;
Address:"Department of Biosystems Engineering, College of Agriculture and Life Sciences, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Korea. Department of Agriculture, Forestry and Bioresources, College of Agriculture and Life Sciences, Seoul National University, Seoul 08826, Korea. Global Smart Farm Convergence Major, College of Agriculture and Life Sciences, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Korea. Research Institute of Agriculture and Life Science, College of Agriculture and Life Sciences, Seoul National University, Seoul 08826, Korea"
Journal Title:Insects
Year:2021
Volume:20210412
Issue:4
Page Number: -
DOI: 10.3390/insects12040342
ISSN/ISBN:2075-4450 (Print) 2075-4450 (Electronic) 2075-4450 (Linking)
Abstract:"The black pine bast scale, M. thunbergianae, is a major insect pest of black pine and causes serious environmental and economic losses in forests. Therefore, it is essential to monitor the occurrence and population of M. thunbergianae, and a monitoring method using a pheromone trap is commonly employed. Because the counting of insects performed by humans in these pheromone traps is labor intensive and time consuming, this study proposes automated deep learning counting algorithms using pheromone trap images. The pheromone traps collected in the field were photographed in the laboratory, and the images were used for training, validation, and testing of the detection models. In addition, the image cropping method was applied for the successful detection of small objects in the image, considering the small size of M. thunbergianae in trap images. The detection and counting performance were evaluated and compared for a total of 16 models under eight model conditions and two cropping conditions, and a counting accuracy of 95% or more was shown in most models. This result shows that the artificial intelligence-based pest counting method proposed in this study is suitable for constant and accurate monitoring of insect pests"
Keywords:Cnn Faster R-CNN Matsucoccus thunbergianae Ssd deep learning insect counting object detection pest monitoring sex pheromone trap;
Notes:"PubMed-not-MEDLINEHong, Suk-Ju Nam, Il Kim, Sang-Yeon Kim, Eungchan Lee, Chang-Hyup Ahn, Sebeom Park, Il-Kwon Kim, Ghiseok eng 2020185B10-2022-AA02/Korea Forest Service/ Switzerland 2021/05/01 Insects. 2021 Apr 12; 12(4):342. doi: 10.3390/insects12040342"

 
Back to top
 
Citation: El-Sayed AM 2024. The Pherobase: Database of Pheromones and Semiochemicals. <http://www.pherobase.com>.
© 2003-2024 The Pherobase - Extensive Database of Pheromones and Semiochemicals. Ashraf M. El-Sayed.
Page created on 05-11-2024