Improved classification of conservation tillage practices using hyperspectral imagery with spatial-spectral features

Wei Li*, Qiong Ran, Qian Du, Chenghai Yang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)

Abstract

Classification of conservation tillage practices from hyper-spectral imagery is challenging due to spectral similarity between soils and senescent crop residues. In this paper, a novel classifier using both spectral and spatial information is proposed for hyperspectral image classification. Three steps are included: (1) a feature extraction method using a very simple local averaging filter to produce the joint spectral-spatial features; (2) an efficient local Fisher discriminant analysis projection for dimensionality reduction and class separability enhancement; and (3) the typical k-nearest neighbor classifier for final classification. Experimental results using real hy-perspectral data demonstrate the benefits of the proposed approach, which can outperform other popular classifiers, such as support vector machine with composite kernel.

Original languageEnglish
Title of host publication2014 The 3rd International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479941575
DOIs
Publication statusPublished - 25 Sept 2014
Externally publishedYes
Event2014 3rd International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2014 - Beijing, China
Duration: 11 Aug 201414 Aug 2014

Publication series

Name2014 The 3rd International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2014

Conference

Conference2014 3rd International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2014
Country/TerritoryChina
CityBeijing
Period11/08/1414/08/14

Keywords

  • Conservation tillage
  • feature extraction
  • hyperspectral data
  • pattern classification

Fingerprint

Dive into the research topics of 'Improved classification of conservation tillage practices using hyperspectral imagery with spatial-spectral features'. Together they form a unique fingerprint.

Cite this