Presentation | 2024-01-26 Development of a measurement AI camera for use in the tomato growing process Yasuhiro Okabe, Keita Endo, Naoki Yamada, Takefumi Hiraguri, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | If it were possible to mechanically estimate when tomatoes should be harvested timing, it would make harvesting easier for inexperienced farmers. Farmers generally judge the best time to harvest tomatoes based on size and ripeness, i.e., color. However, inexperienced farmers make judgments based on their own subjective judgments, making it difficult to harvest tomatoes of uniform quality. In this study, we propose a technique for measuring tomato size and color using image analysis technology. The proposed method uses machine learning to identify tomato objects based on YOLO (You Only Look Once) from image data captured by a camera, and then calculates the number of image pixel count in each tomato. In addition, LiDAR (Light Detection And Ranging) technology is used to determine the depth, or distance from the camera to the tomato. The size of multiple tomatoes can be simultaneously measured based on the object identification, image pixel count, and distance using YOLO. Hue is calculated from HSV (color space), and the degree of ripeness is estimated by classifying the color of tomatoes. HSV is characterized by its ability to identify color differences based on wavelengths, which allows accurate color classification even in greenhouse fields with different luminance and light levels depending on weather and time of day, thus ensuring accurate color ripeness at all times. We have developed an implementation of these technologies in an AI camera, which is currently being installed in a greenhouse field and is being tested. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Smart agriculture / LiDAR / YOLO / HSV / Ripeness Classification |
Paper # | CQ2023-66 |
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) | Development of a measurement AI camera for use in the tomato growing process |
Sub Title (in English) | |
Keyword(1) | Smart agriculture |
Keyword(2) | LiDAR |
Keyword(3) | YOLO |
Keyword(4) | HSV |
Keyword(5) | Ripeness Classification |
1st Author's Name | Yasuhiro Okabe |
1st Author's Affiliation | Nippon Institute of Technology(NIT) |
2nd Author's Name | Keita Endo |
2nd Author's Affiliation | Nippon Institute of Technology(NIT) |
3rd Author's Name | Naoki Yamada |
3rd Author's Affiliation | Nippon Institute of Technology(NIT) |
4th Author's Name | Takefumi Hiraguri |
4th Author's Affiliation | Nippon Institute of Technology(NIT) |
Date | 2024-01-26 |
Paper # | CQ2023-66 |
Volume (vol) | vol.123 |
Number (no) | CQ-368 |
Page | pp.pp.76-81(CQ), |
#Pages | 6 |
Date of Issue | 2024-01-18 (CQ) |