A Laboratory Test of Paddy Yellowing Rate Estimation Technique for Smart Agriculture

Abstract

This paper describes a laboratory test result of paddy yellowing rate estimation technique for smart agriculture. The paddy yellowing rate is important for determining the proper time of harvesting. It is required to measure the paddy yellowing rate in the field by image analysis. Since, this technological development is extremely difficult, this laboratory test was conducted as a preliminary step. The study area is Hozaki area in Akaiwa city and Shinogoze area in Okayama city, Okayama prefecture. Sampling and laboratory tests were conducted on 7^th October in 2019 and 9^th October in 2020, these times are 1 or 2 weeks before harvest. The number of sampling points is 47, three ears were collected from each point. The ear was photographed with Olympus digital camera, TG-5. Image data converted from raw to TIFF data. The paddy yellowing rate was calculated by dividing the number of blue seeds, means immature, by the total seeds. The explanatory variables were normalized difference vegetation index that combined two bands from blue, green and red band. As a result of the analysis using 2019 data, a linear regression model with the highest correlation coefficient (R ; 0.77) could be built by the normalized difference vegetation index using the combination of red and green band. An estimation model using 2020 data could not be constructed. It is probable that the ripening of this year was more advanced than previous year. From the result, it could be considered that the proposed method can be applied before the late ripening period.