| Presentation | 2024-01-26 Estimating the best time to collect pear pollen using deep learning Keita Endo, Tomotaka Kimura, Hiroyuki Shimizu, Tomohito Shimada, Akane Shibasaki, Ryota Fujinuma, Yoshihiro Takemura, Takefumi Hiraguri, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Pear pollination is generally done by artificial pollination, and pollen collection is necessary for artificial pollination. Pollen collection is hard work, requiring long hours at high altitudes, and in recent years, much of the pollen is imported. However, if an important disease occurs in a pollen exporting country, imports are stopped, resulting in a decrease in production. To solve this problem, it is necessary to mechanize the pollen collection process and strengthen the domestic supply and demand system. In this study, we propose an AI (Artificial Intelligence)-based method for estimating pear pollen quantity. Specifically, we use YOLO (You Only Look Once), a deep learning-based object detection algorithm, to detect pear blossoms on photographed branches by classifying them into five stages, from bud to blossom. The amount of pollen per branch is calculated from the number of flowers in each flowering stage detected and the average amount of pollen per flower. In this paper, we report on the evaluation of the estimation accuracy of AI-based pear pollen quantity estimation developed by assessing the classification accuracy and detection precision during the detection of blooming stages using YOLO. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Smart agriculture / Machine learning / YOLO / Pear / Estimation of pollen amount |
| Paper # | CQ2023-65 |
| Date of Issue | 2024-01-18 (CQ) |
| Conference Information | |
| Committee | CQ |
|---|---|
| Conference Date | 2024/1/25(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Kurokawa-Onsen |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Network Science, Computational Social Science, Media Quality, Communication Behaviour, etc. |
| Chair | Takefumi Hiraguri(Nippon Inst. of Tech.) |
| Vice Chair | Takahiro Matsuda(Tokyo Metropolitan Univ.) / Gou Hasegawa(Tohoku Univ.) / Sumaru Niida(KDDI Research) |
| Secretary | Takahiro Matsuda(NTT) / Gou Hasegawa(Tama Univ.) / Sumaru Niida(Tsukuba Univ.) |
| Assistant | Ryo Nakamura(Fukuoka Univ.) / Toshiro Nakahira(NTT) / Kenta Tsukatsune(Okayama Univ. of Science) |
| Paper Information | |
| Registration To | Technical Committee on Communication Quality |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Estimating the best time to collect pear pollen using deep learning |
| Sub Title (in English) | |
| Keyword(1) | Smart agriculture |
| Keyword(2) | Machine learning |
| Keyword(3) | YOLO |
| Keyword(4) | Pear |
| Keyword(5) | Estimation of pollen amount |
| 1st Author's Name | Keita Endo |
| 1st Author's Affiliation | Nippon Institute of Technology(NIT) |
| 2nd Author's Name | Tomotaka Kimura |
| 2nd Author's Affiliation | Doshisha University(Doshisha Univ.) |
| 3rd Author's Name | Hiroyuki Shimizu |
| 3rd Author's Affiliation | Nippon Institute of Technology(NIT) |
| 4th Author's Name | Tomohito Shimada |
| 4th Author's Affiliation | Saitama Agricultural Technology Research Center(SATRC) |
| 5th Author's Name | Akane Shibasaki |
| 5th Author's Affiliation | Saitama Agriculture and Forestry Promotion Center(SAFPC) |
| 6th Author's Name | Ryota Fujinuma |
| 6th Author's Affiliation | DKK Co., Ltd.(DKK) |
| 7th Author's Name | Yoshihiro Takemura |
| 7th Author's Affiliation | Tottori University(Tottori Univ.) |
| 8th Author's Name | Takefumi Hiraguri |
| 8th Author's Affiliation | Nippon Institute of Technology(NIT) |
| Date | 2024-01-26 |
| Paper # | CQ2023-65 |
| Volume (vol) | vol.123 |
| Number (no) | CQ-368 |
| Page | pp.pp.68-75(CQ), |
| #Pages | 8 |
| Date of Issue | 2024-01-18 (CQ) |