| タイトル | Plant features measurements for robotics |
| 本文（外部サイト） | http://hdl.handle.net/2060/19900007379 |
| 著者（英） | Miles, Gaines E. |
| 著者所属（英） | Purdue Univ. |
| 発行日 | 1989-10-01 |
| 言語 | eng |
| 内容記述 | Initial studies of the technical feasibility of using machine vision and color image processing to measure plant health were performed. Wheat plants were grown in nutrient solutions deficient in nitrogen, potassium, and iron. An additional treatment imposed water stress on wheat plants which received a full complement of nutrients. The results for juvenile (less than 2 weeks old) wheat plants show that imaging technology can be used to detect nutrient deficiencies. The relative amount of green color in a leaf declined with increased water stress. The absolute amount of green was higher for nitrogen deficient leaves compared to the control plants. Relative greenness was lower for iron deficient leaves, but the absolute green values were higher. The data showed patterns across the leaf consistent with visual symptons. The development of additional color image processing routines to recognize these patterns would improve the performance of this sensor of plant health. |
| NASA分類 | LIFE SCIENCES (GENERAL) |
| レポートNO | 90N16695 |
| 権利 | No Copyright |
| URI | https://repository.exst.jaxa.jp/dspace/handle/a-is/139145 |
|
