Integration of spatial and spectral information by means of unsupervised extraction and classification for homogenous objects applied to multispectral and hyperspectral data

IEEE Transactions on Geoscience and Remote SensingPublished 1 April 2005

Luís Ortiz Jiménez, Jorge Rivera-Medina, Eladio Rodriguez‐Diaz, Emmanuel Arzuaga, Robinson Ramírez‐Vélez

DOI10.1109/tgrs.2004.843193

Source URL

Citations84

SJR quartileQ1

SJR score2.40

SNIP2.37

TL;DR

This mechanism will enable an unsupervised contextual classification of multispectral data that integrates the spectral and spatial information producing results that are more meaningful to the human analyst.

Abstract

This paper presents a method of unsupervised enhancement of pixels homogeneity in a local neighborhood. This mechanism will enable an unsupervised contextual classification of multispectral data that integrates the spectral and spatial information producing results that are more meaningful to the human analyst. This unsupervised classifier is an unsupervised development of the well-known supervised extraction and classification for homogenous objects (ECHO) classifier. One of its main characteristics is that it simplifies the retrieval process of spatial structures. This development is specially relevant for the new generation of airborne and spaceborne sensors with high spatial resolution.

Keywords

EngineeringEnvironmental Science

Remote Sensing Digital Image Analysis: An Introduction

2,897 Citations1999John A. Richards

Medical Entomology and ZoologyLight and Water: Radiative Transfer in Natural Waters

2,181 Citations1994Curtis D. Mobley

Remote Sensing Digital Image Analysis

939 Citations1993John A. Richards

IEEE Transactions on Pattern Analysis and Machine Intelligence2-D shape classification using hidden Markov model

165 Citations1991Yulin He, A. Kundu

The authors present a planar shape recognition approach based on the hidden Markov model and autoregressive parameters that segments closed shapes to make classifications at a finer level and does not have to be trained again when a new class of shapes is added.

Pattern RecognitionThe development of a spectral-spatial classifier for earth observational data

140 Citations1980D. A. Landgrebe

An overview of the conception, development, evaluation and documentation of this spectral-spatial classifier for earth observational image data shows it to have improved accuracy, with greater computation efficiency, and only slightly increased operator complexity.

Journal of the Royal Statistical Society Series A (Statistics in Society)Discriminant Analysis and Statistical Pattern Recognition.

74 Citations1993Ian Ford, Geoffrey J. McLachlan

Advances covered are: regularized discriminant analysis and bootstrap-based assessment of the performance of a sample-based discriminant rule and extensions of discriminantAnalysis motivated by problems in statistical image analysis.

IEEE Transactions on Image ProcessingImage classification using spectral and spatial information based on MRF models

40 Citations1995T. Yamazaki, Denis Gingras

A new criterion for classifying multispectral remote sensing images or textured images by using spectral and spatial information is proposed and a stepwise classification algorithm is derived.

Optical EngineeringContextual clustering for image segmentation

26 Citations2000Andrea Baraldi

A modified PAC (MPAC) scheme centered on a novel class-conditional model, which employs local and global spectral estimates simulta- neously is presented, showing that MPAC is superior to contextual PAC and stochastic expectation-maximization as well as to noncontextual clustering algorithms in detecting image details.

Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Integration of spatial and spectral information in unsupervised classification for multispectral and hyperspectral data</title>

10 Citations1999Luis O. Jiménez-Rodríguez, Jorge Rivera-Medina

This paper will present an unsupervised classification system developed to extract information from multispectral and hyperspectral data as well, considering the spectral response, hyperdimensional data characteristics, and the spatial context of the pixel that will be classified.