AUTHOR=Ma Yiru , Ma Lulu , Zhang Qiang , Huang Changping , Yi Xiang , Chen Xiangyu , Hou Tongyu , Lv Xin , Zhang Ze 

TITLE=Cotton Yield Estimation Based on Vegetation Indices and Texture Features Derived From RGB Image

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.925986

DOI=10.3389/fpls.2022.925986

ISSN=1664-462X

ABSTRACT=Yield monitoring is an important parameter to evaluate cotton productivity during cotton har-vest. Nondestructive and accurate yield monitoring is of great significance to cotton production. Unmanned aerial vehicle (UAV) remote sensing has fast and repetitive acquisition ability. The visible vegetation indices has the advantages of low cost, small calculation and high resolution, The combination of the UAV and visible vegetation indices has been more and more applied to crop yield monitoring. However, there are some defects in estimating cotton yield based on visible vegetation indices only: The color of cotton and film was similar and the vegetation indices corresponding to different yields might be saturated. Texture feature is another important re-mote sensing information that can provide geometric information of ground objects and enlarge the spatial information identification based on original image brightness. In this study, RGB images of cotton canopy were acquired by UAV carrying RGB sensors before cotton harvest. The visible vegetation indices and texture features were extracted from RGB images for cotton yield monitoring. feature parameters were selected in different methods after extracting the information. Linear and nonlinear methods were used to construct cotton yield monitoring models based on visible vegetation indices, texture features and their combinations,. The results show that, (1) The vegetation indices and texture features extracted from the ultra-high-resolution RGB images obtained by UAVs were significantly correlated with the cotton yield; (2) The accuracy of yield monitoring model based on vegetation indices varies greatly, and the verification set R² was 0.2494-0.6992, RMSE was 2.9596 -1.4763 t/ha, rRMSE was 76.62 - 49.23%. Based on texture features, verification set, R² was 0.2391 - 0.8379; RMSE was 2.7222 - 1.1705 t/ha, rRMSE was 82.12 - 34.54%. Combined with vegetation indices and texture characteristics, verification set R² was 0.3348 - 0.9109; RMSE was 2.5277 - 0.91277 t/ha. rRMSE was 72.82 - 29.34%. In conclusion, the re-search results prove that UAV carrying RGB sensor has a certain potential in cotton yield monitoring, which can provide theoretical basis and technical support for field cotton production evaluation.