Combining Spectral and Texture Features of UAS-Based Multispectral Images for Maize Leaf Area Index Estimation

Xuewei Zhang,Yu Chen,Yumeng Hao,Huifu Zhuang,Jinxiang Liu,Yindi Zhao,Erjiang Fu,Kefei Zhang,Shuo Chen,Wei Ban,Yaqin Sun

doi:10.3390/rs14020331

Xuewei Zhang, Yu Chen + Show 9 more

Open Access

https://doi.org/10.3390/rs14020331

Copy DOI

Abstract

The leaf area index (LAI) is of great significance for crop growth monitoring. Recently, unmanned aerial systems (UASs) have experienced rapid development and can provide critical data support for crop LAI monitoring. This study investigates the effects of combining spectral and texture features extracted from UAS multispectral imagery on maize LAI estimation. Multispectral images and in situ maize LAI were collected from test sites in Tongshan, Xuzhou, Jiangsu Province, China. The spectral and texture features of UAS multispectral remote sensing images are extracted using the vegetation indices (VIs) and the gray-level co-occurrence matrix (GLCM), respectively. Normalized texture indices (NDTIs), ratio texture indices (RTIs), and difference texture indices (DTIs) are calculated using two GLCM-based textures to express the influence of two different texture features on LAI monitoring at the same time. The remote sensing features are prescreened through correlation analysis. Different data dimensionality reduction or feature selection methods, including stepwise selection (ST), principal component analysis (PCA), and ST combined with PCA (ST_PCA), are coupled with support vector regression (SVR), random forest (RF), and multiple linear regression (MLR) to build the maize LAI estimation models. The results reveal that ST_PCA coupled with SVR has better performance, in terms of the VIs + DTIs (R2 = 0.876, RMSE = 0.239) and VIs + NDTIs (R2 = 0.877, RMSE = 0.236). This study introduces the potential of different texture indices for maize LAI monitoring and demonstrates the promising solution of using ST_PCA to realize the combining of spectral and texture features for improving the estimation accuracy of maize LAI.

Highlights

Introduction iationsThe leaf area index (LAI), which is defined as the ratio of one-sided leaf area per unit of ground area [1], is closely related to the respiration, transpiration, and photosynthesis of vegetation [2,3,4,5]
To determine the relationship between in situ maize LAI and spectral features derived from multispectral unmanned aerial systems (UASs) data, a correlation analysis between the LAI and six vegetation indices (VIs) was conducted
The results indicated that most VIs had a good correlation with LAI (Table 4), among which NDVIRE and MSRRE had higher correlation

Summary

Introduction

Introduction iationsThe leaf area index (LAI), which is defined as the ratio of one-sided leaf area per unit of ground area [1], is closely related to the respiration, transpiration, and photosynthesis of vegetation [2,3,4,5]. An accurate estimation of LAI is of great significance for monitoring crop growth, health, and yield prediction [6,7,8]. Traditional LAI monitoring methods require destructive sampling, which is time-consuming and labor-intensive [9,10]. The remote sensing inversion method can realize the non-destructive, fast, and accurate LAI estimation [11,12]. Satellite platforms, which can obtain spectral information for a wide range of ground objects, have been widely applied in crop LAI monitoring in recent years [13,14]. Landsat-8 OLI satellite image data have been used for LAI estimations of tropical forests in India [15]. Mao et al [16], based on the Sentinel-2 satellite image data, compared the differences of different machine learning algorithms for cotton

Methods

Results

Discussion

Conclusion