Method and system for identifying plant species based on hyperspectral data

US10663445B2 · kind B2 · utility

Inventors

• Guoqiang Wang · Shandong, CN
• Puze Wang · Beijing, CN
• Yanbo Peng · Beijing, CN
• Ruimin Li · Beijing, CN
• Tingxi Liu · Beijing, CN
• Wei Wang · Beijing, CN
• Yinglan A · Beijing, CN

Key dates

• Filing date: May 6, 2018
• Grant date: May 26, 2020
• Expiry date: Dec 6, 2038

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V20/194
• WIPO field: Measurement
• WIPO sector: Instruments

Abstract

The present disclosure provides a method and system for identifying plant species based on hyperspectral data, wherein the method includes: performing atmospheric radiation correction for the hyperspectral data of plants to be identified adopting Linear Regression method, to obtain corrected hyperspectral data, wherein, the hyperspectral data of the plants to be identified are collected by a hyperspectral ground object spectrometer provided within an unmanned aerial vehicle (UAV); performing external parameter orthogonalisation (EPO) processing for the corrected hyperspectral data; performing first order differential processing for the EPO processed hyperspectral data, to obtain hyperspectral data highlighting absorption peak information; performing discrete wavelet transformation processing for the hyperspectral data highlighting the absorption peak information, to obtain wavelet coefficients corresponding to the plants to be identified.