AUTHOR=Wang Fumin , Yi Qiuxiang , Xie Lili , Yao Xiaoping , Zheng Jueyi , Xu Tianyue , Li Jiale , Chen Siting 

TITLE=Non-destructive monitoring of amylose content in rice by UAV-based hyperspectral images

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.1035379

DOI=10.3389/fpls.2022.1035379

ISSN=1664-462X

ABSTRACT=Amylose content (AC) is an important indicator for rice quality grading. The rapid development of UAV (Unmanned Aerial Vehicle) technology provides rich spectral and spatial information on observed objects, making non-destructive monitoring of crop quality possible. To test the potential of UAV-based hyperspectral images in AC estimation, in this study, observations on 5 rice cultivars were carried out in eastern China (Zhejiang province) for four consecutive years (from 2017 to 2020). The correlationships between spectral as well as textural variables of UAV-based hyperspectral images at different growth stages (the booting, heading, filling and ripening stages) and amylose content (%) were analyzed, and the linear regression models based on spectral variables alone, textural variables alone and combined spectral and textural variables were established. The results showed that the sensitive bands (P<0.001) to AC were mainly centered in the green (536 nm  568 nm) and red regions (630 nm  660 nm), with spectral and textural variables at the ripening stage giving the highest negative correlation coefficient of -0.868 and -0.824, respectively. Models based on spectral combining textural variables give the better estimation than those based on spectral or textural variables alone, characterized with less variables and higher accuracy. The best models using spectral or textural variables alone were both involved three growth stages (the heading, filling and ripening stage), with the RMSE (Root Mean Squared Error) of 1.01% and 1.04%, respectively, while the models based on combined spectral and textural variables have the RMSE of 1.04% 0.844% with only one (the ripening stage) or two (the ripening and filling stages) growth stages were involved. The combination of spectral variables with textural measures is expected to simplify data acquisition and meanwhile enhance estimation accuracy in remote sensing of rice AC.