Result: BP neural network based SubPixel mapping method

Title:
BP neural network based SubPixel mapping method
Authors:
LIGUO WANG, YE ZHANG, JIAO LI
Source:
Intelligent computing in signal processing and pattern recognition (International Conference on Intelligent Computing, ICIC 2006, Kunming, China, August 16-19, 2006)0ICIC 2006. :755-760
Publisher Information:
Berlin: Springer, 2006.
Publication Year:
2006
Physical Description:
print, 10 ref 1
Original Material:
INIST-CNRS
Subject Terms:
Control theory, operational research, Automatique, recherche opérationnelle, Documentation, Computer science, Informatique, Telecommunications, Télécommunications, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Intelligence artificielle, Artificial intelligence, Algorithme apprentissage, Learning algorithm, Algoritmo aprendizaje, Algorithme rétropropagation, Backpropagation algorithm, Algoritmo retropropagación, Analyse algorithme, Algorithm analysis, Análisis algoritmo, Capteur imagerie hyperspectral, Hyperspectral imaging sensor, Sensor hiperespectral de formación de imágenes, Complexité calcul, Computational complexity, Complejidad computación, Intelligence artificielle, Artificial intelligence, Inteligencia artificial, Loi échelle, Scaling law, Ley escala, Modèle réduit, Scale model, Modelo reducido, Modélisation, Modeling, Modelización, Répartition spatiale, Spatial distribution, Distribución espacial, Réseau neuronal, Neural network, Red neuronal, Résolution spatiale, Spatial resolution, Resolución espacial
Document Type:
Conference Conference Paper
File Description:
text
Language:
English
Author Affiliations:
School of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China
Dept. of Information Engineering, Harbin Institute of Technology, Harbin 150001, China
ISSN:
0170-8643
Access URL:
http://pascal-francis.inist.fr/vibad/index.php?action=search&terms=18315903
Rights:
Copyright 2006 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Computer science; theoretical automation; systems
Accession Number:
edscal.18315903
Database:
PASCAL Archive

Further Information

A new subpixel mapping method based on BP neural network is proposed to improve spatial resolution of both raw hyperspectral imagery (HSI) and its fractional image. The network is used to train a model that describes the relationship between mixed pixel accompanied by its neighbors and the spatial distribution within the pixel. Then mixed pixel can be super-resolved by the trained model in subpixel scale. To improve the mapping performance, momentum is employed in BP learning algorithm and local analysis is adopted in processing of raw HSI. The comparison experiments are conducted both on synthetic images and on truth HSI. The results prove that the method has fairly good mapping effect and very low computational complexity for processing both of raw HSI and of fractional image.