• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2023 Fiscal Year Final Research Report

Development of image processing algorithm to assist beekeeping

Research Project

  • PDF
Project/Area Number 21K11931
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 61010:Perceptual information processing-related
Research InstitutionUtsunomiya University

Principal Investigator

Hasegawa Madoka  宇都宮大学, 工学部, 教授 (80322014)

Project Period (FY) 2021-04-01 – 2024-03-31
Keywords画像解析 / ミツバチ / 巣 / 機械学習 / 画像処理 / ヘギイタダニ
Outline of Final Research Achievements

The purpose of this study is to apply image processing technology to the management of honeybee colonies. Specifically, we studied on methods to measure the distribution of brood cells and the number of bees from images of honeycombs. In this study, we developed techniques using semantic segmentation and methods using SSD (Single Shot MultiBox Detector).
Additionally, we studied on automatic measurement methods for Varroa mite infestation from images taken inside the hive. Focusing on the natural fall method, a type of mite infestation rate inspection, we investigated a method to count mites that fell onto white paper placed at the bottom of the hive and developed an Android application for this purpose. We also examined methods to detect mites parasitizing on the bees' backs.

Free Research Field

画像工学

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を利用した作業支援に期待が寄せられている.
本研究では,蜂巣状態の把握の効率化を目的とし,巣板を撮影した画像をAIで分析し,巣板上の幼虫,さなぎ,蜜などの分布を計測する手法や,巣板表面に密集するハチ個体を計数する手法を開発した.さらに,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,自動計数するアプリの開発も行った.これら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.

URL: 

Published: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi