20181123

Author : 

Shengyao Jia, Hongyang Li, Yanjie Wang, Renyuan Tong and Qing Li

Year : 2017

Title : Hyperspectral Imaging Analysis for the Classification of Soil Types and the Determination of Soil Total Nitrogen

Journal :  Sensors

Comment 


 In this work, hyperspectral imaging (HSI) technology was applied for the classification of soil types and the measurement of soil total nitrogen (TN) content. A total of 183 soil samples collected from Shangyu City (People’s Republic of China), were scanned by a near-infrared hyperspectral imaging system with a wavelength range of 874–1734 nm. 

 The successive projections algorithm (SPA) method was utilized to select effective wavelengths from the full spectrum. Pattern texture features (energy, contrast, homogeneity and entropy) were extracted from the gray-scale images at the effective wavelengths. The support vector machines (SVM) and partial least squares regression (PLSR) methods were used to establish classification and prediction models, respectively. The results showed that by using the combined data sets of effective wavelengths and texture features for modelling an optimal correct classification rate of 91.8% could be achieved. The overall results indicated that hyperspectral imaging technology could be used for soil type classification and soil TN determination, and data fusion combining spectral and image texture information showed advantages for the classification of soil types.

댓글

이 블로그의 인기 게시물

20190405

20181130

Climate warming alters subsoil but not topsoil carbon dynamics in alpine grassland