Image-based analysis of brood condition in honey bee combs
Project/Area Number |
18K11346
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 61010:Perceptual information processing-related
|
Research Institution | Utsunomiya University |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
篠田 一馬 宇都宮大学, 工学部, 准教授 (50639200)
|
Project Period (FY) |
2018-04-01 – 2022-03-31
|
Project Status |
Completed (Fiscal Year 2021)
|
Budget Amount *help |
¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2020: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2018: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
Keywords | 画像解析 / ミツバチ / 巣 / 機械学習 / 画像処理 / 養蜂用巣脾 / CNN / 蜂巣画像 |
Outline of Final Research Achievements |
The shortage of honeybee has become a problem. Although monitoring of honeycomb is important to prevent this problem, visual inspection by human requires long working hours. Therefore, it is expected to improve the efficiency of the inspection process by a computer-assisted approach. In this study, we studied on the monitoring support system of honeybee nest. We have constructed a database of honeycomb and Varroa mite images to carry out the study. Using the images of the honeycomb taken through this study, we investigated the method of detecting and classifying cells by CNN, SSD, and Feature fusion SSD. We also studied on the image-based measurement of naturally fallen Varroa mites. We developed an Android application and examined its performance. This application enables us to measure the mite parasitism rate with a smartphone or tablet.
|
Academic Significance and Societal Importance of the Research Achievements |
養蜂では蜂巣の点検が人手で行われているが,作業に多大な労力を要しているため,ITを利用した点検作業の支援に期待が寄せられている. 本研究では,蜂巣の育房状態の把握の効率化を目的とし,巣脾を撮影した画像をAIで分析し,育房が幼虫やさなぎの生育,蜜や花粉の貯蔵等のどの状態にあるかを自動判別する手法を検討した.また,巣箱の底を撮影した画像から,ミツバチに寄生するミツバチヘギイタダニを検出し,自動計数する手法の検討も行った.これら手法を構築できたことで,ミツバチ大量死の原因究明と巣箱の日常モニタリングに役立てることが可能となり,養蜂業およびミツバチを利用する各種農業に貢献できると考えられる.
|
Report
(5 results)
Research Products
(12 results)