Classification of Soil Types Using Hyperspectral Imaging Technology

S. Y. Jia, H. Y. Li, C. X. Miao, Q. Li

Abstract

Soil type is a key indicator in field survey, but the current soil classification method largely depends on personal experiences of operators. In this work, hyperspectral imaging (HSI) technology was applied for the fast and accurate classification of soil types. 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 the wavelength range of 874-1734 nm. The soil samples belonged to three major soil types of this area, included paddy soil, red soil and seashore saline soil. The method of successive projections algorithm (SPA) 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 method of support vector machines (SVM) was used to establish classification models. The results showed that: using the combined data sets of effective wavelengths and texture features for modelling reached the optimal correct classification rate of 91.8%. The results indicated that hyperspectral imaging technology could be used for soil type classification, and data fusion combining spectral and image texture information showed advantages for the classification of soil types.

Download


Paper Citation


in Harvard Style

Jia S., Li H., Miao C. and Li Q. (2018). Classification of Soil Types Using Hyperspectral Imaging Technology.In Proceedings of the International Workshop on Environmental Management, Science and Engineering - Volume 1: IWEMSE, ISBN 978-989-758-344-5, pages 502-511. DOI: 10.5220/0007562505020511


in Bibtex Style

@conference{iwemse18,
author={S. Y. Jia and H. Y. Li and C. X. Miao and Q. Li},
title={Classification of Soil Types Using Hyperspectral Imaging Technology},
booktitle={Proceedings of the International Workshop on Environmental Management, Science and Engineering - Volume 1: IWEMSE,},
year={2018},
pages={502-511},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007562505020511},
isbn={978-989-758-344-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the International Workshop on Environmental Management, Science and Engineering - Volume 1: IWEMSE,
TI - Classification of Soil Types Using Hyperspectral Imaging Technology
SN - 978-989-758-344-5
AU - Jia S.
AU - Li H.
AU - Miao C.
AU - Li Q.
PY - 2018
SP - 502
EP - 511
DO - 10.5220/0007562505020511