Li Changming, Teng Xing, Tan Yong, Zhang Yong, Zhang Hongchen, Xiao Dan, Luo Shanjun
Engineering Technology Research and Development Center, Changchun Guanghua University, Changchun, China.
Rural Energy and Ecological Research Institute, Jilin Academy of Agricultural Sciences, Changchun, China.
Front Plant Sci. 2024 Sep 6;15:1445490. doi: 10.3389/fpls.2024.1445490. eCollection 2024.
Monitoring the leaf area index (LAI), which is directly related to the growth status of rice, helps to optimize and meet the crop's fertilizer requirements for achieving high quality, high yield, and environmental sustainability. The remote sensing technology of the unmanned aerial vehicle (UAV) has great potential in precision monitoring applications in agriculture due to its efficient, nondestructive, and rapid characteristics. The spectral information currently widely used is susceptible to the influence of factors such as soil background and canopy structure, leading to low accuracy in estimating the LAI in rice.
In this paper, the RGB and multispectral images of the critical period were acquired through rice field experiments. Based on the remote sensing images above, the spectral indices and texture information of the rice canopy were extracted. Furthermore, the texture information of various images at multiple scales was acquired through resampling, which was utilized to assess the estimation capacity of LAI.
The results showed that the spectral indices (SI) based on RGB and multispectral imagery saturated in the middle and late stages of rice, leading to low accuracy in estimating LAI. Moreover, multiscale texture analysis revealed that the texture of multispectral images derived from the 680 nm band is less affected by resolution, whereas the texture of RGB images is resolution dependent. The fusion of spectral and texture features using random forest and multiple stepwise regression algorithms revealed that the highest accuracy in estimating LAI can be achieved based on SI and texture features (0.48 m) from multispectral imagery. This approach yielded excellent prediction results for both high and low LAI values. With the gradual improvement of satellite image resolution, the results of this study are expected to enable accurate monitoring of rice LAI on a large scale.
监测叶面积指数（LAI）与水稻生长状况直接相关，有助于优化并满足作物的肥料需求，以实现优质、高产和环境可持续性。无人机（UAV）遥感技术因其高效、无损和快速的特点，在农业精准监测应用中具有巨大潜力。目前广泛使用的光谱信息易受土壤背景和冠层结构等因素影响，导致水稻叶面积指数估算精度较低。
本文通过稻田试验获取关键时期的RGB和多光谱图像。基于上述遥感图像，提取水稻冠层的光谱指数和纹理信息。此外，通过重采样获取多尺度下各种图像的纹理信息，用于评估叶面积指数的估算能力。
结果表明，基于RGB和多光谱图像的光谱指数在水稻生长中后期饱和，导致叶面积指数估算精度较低。此外，多尺度纹理分析表明，源自680nm波段的多光谱图像纹理受分辨率影响较小，而RGB图像纹理依赖于分辨率。使用随机森林和多元逐步回归算法融合光谱和纹理特征表明，基于多光谱图像的光谱指数和纹理特征（0.48米）估算叶面积指数可实现最高精度。该方法对高叶面积指数值和低叶面积指数值均产生了优异的预测结果。随着卫星图像分辨率的逐步提高，本研究结果有望实现对水稻叶面积指数的大规模准确监测。
