Hybrid adaptive prediction mechanisms with multilayer propagation neural network for hyperspectral image compression

Research output: Book chapter/Published conference paperConference paperpeer-review

Abstract

Hyperspectral (HS) image is a three dimensional data image where the 3rd dimension carries the wealth of spectrum information. HS image compression is one of the areas that has attracted increasing attention for big data processing and analysis. HS data has its own distinguishing feature which differs with video because without motion, also different with a still image because of redundancy along the wavelength axis. The prediction based method is playing an important role in the compression and research area. Reflectance distribution of HS based on our analysis indicates that there is some nonlinear relationship in intra-band. The Multilayer Propagation Neural Networks (MLPNN) with backpropagation training are particularly well suited for addressing the approximation function. In this paper, an MLPNN based predictive image compression method is presented. We propose a hybrid Adaptive Prediction Mechanism (APM) with MLPNN model (APM-MLPNN). MLPNN is trained to predict the succeeding bands by using current band information. The purpose is to explore whether MLPNN can provide better image compression results in HS images. Besides, it uses less computation cost than a deep learning model so we can easily validate the model. We encoded the weights vector and the bias vector of MLPNN as well as the residuals. That is the only few bytes it then sends to the decoder side. The decoder will reconstruct a band by using the same structure of the network. We call it an MLPNN decoder. The MLPNN decoder does not need to be trained as the weights and biases have already been transmitted. We can easily reconstruct the succeeding bands by the MLPNN decoder. APM constrained the correction offset between the succeeding band and the current spectral band in order to prevent HS image being affected by large predictive biases. The performance of the proposed algorithm is verified by several HS images from Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) reflectance dataset. MLPNN simulation results can improve prediction accuracy; reduce residual of intra-band with high compression ratio and relatively lower bitrates.
Original languageEnglish
Title of host publicationImage and Video Technology
Subtitle of host publication8th Pacific-Rim Symposium (PSIVT 2017) Revised Selected Papers
EditorsManoranjan Paul, Carlos Hitoshi, Qingming Huang
Place of PublicationSwitzerland
PublisherSpringer
Pages162-173
Number of pages12
Volume10749
ISBN (Electronic)9783319757865
ISBN (Print)9783319757858
DOIs
Publication statusPublished - 2018
Event8th Pacific-Rim Symposium on Image and Video Technology: PSIVT 2017 - Yifu International Convention Center, Wuhan, China
Duration: 20 Nov 201724 Nov 2017
https://web.archive.org/web/20171009074535/http://www.psivt2017.org/ (Conference website)
https://web.archive.org/web/20171022233417/http://www.psivt2017.org/call_for_papers.html (Call for papers)

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume10749
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference8th Pacific-Rim Symposium on Image and Video Technology
Country/TerritoryChina
CityWuhan
Period20/11/1724/11/17
OtherThe Pacific-Rim Symposium on Image and Video Technology (PSIVT) is a high-quality series of symposia that aim at providing a forum for researchers and practitioners who are being involved, or are contributing to theoretical advances or practical implementations in image and video technology.

Previous issues of PSIVT have been held at Hsinchu, Taiwan (2006), Santiago, Chile(2007), Tokyo, Japan (2009), Gwangju, South Korea (2011), Singapore (2010), Guanajuato, Mexico (2013), and Auckland, New Zealand (2015). This eighth issue is being held at Wuhan, China.
Internet address

Fingerprint

Dive into the research topics of 'Hybrid adaptive prediction mechanisms with multilayer propagation neural network for hyperspectral image compression'. Together they form a unique fingerprint.

Cite this