AUTHOR=Zhou Cong , Gong Yan , Fang Shenghui , Yang Kaili , Peng Yi , Wu Xianting , Zhu Renshan 

TITLE=Combining spectral and wavelet texture features for unmanned aerial vehicles remote estimation of rice leaf area index

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.957870

DOI=10.3389/fpls.2022.957870

ISSN=1664-462X

ABSTRACT=The accurate acquisition of crop leaf area index (LAI) may significantly improve the accuracy of crop growth monitoring and yield estimation in agricultural remote sensing. In recent years, the unmanned aerial vehicle (UAV) has developed rapidly and has been widely used in crop remote sensing (RS). Vegetation index (VI) is still a commonly used RS method in LAI estimation. However, VI only reflects the spectral information of the images, ignoring the texture information that can reflect the changes of canopy structure, so it is hard to reflect the complex morphological changes of rice at different growth stages. In this study, we developed a method to improve the estimation accuracy of rice LAI during the whole growing season by combining texture information based on wavelet transform and spectral information derived from VI. During the whole growth period, the images of two study areas located in Hainan and Hubei were obtained by using a 12-band camera. Several VI values were calculated, and the texture analysis was carried out. After the mathematical combination of spectral spectrum and texture features, new indices were constructed. Compared with the corresponding VIs, the new indices reduced the saturation effect and were less sensitive to the emergence of panicles. The determination coefficient (R2) can be improved for all tested VIs throughout the entire growing season of rice. The results showed that the estimation accuracy of LAI by combining spectral information and texture information was higher than that of VIs. This method only used the texture and spectral features of UAV images to establish a model of the whole growth period, which was easy to operate and had great potential for large-scale auxiliary rice breeding and field management research.