Hybrid Adaptive Prediction Mechanisms with Multilayer Propagation Neural Network for Hyperspectral Image Compression

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.

[1]  Bormin Huang,et al.  Lossless Compression of Hyperspectral Images Using Clustered Linear Prediction With Adaptive Prediction Length , 2012, IEEE Geoscience and Remote Sensing Letters.

[2]  Massimo Zucchetti,et al.  A survey of landmine detection using hyperspectral imaging , 2017 .

[3]  V. K. Govindan,et al.  Arithmetic Coding- A Reliable Implementation , 2013 .

[4]  Enrico Magli,et al.  Constant SNR, Rate Control, and Entropy Coding for Predictive Lossy Hyperspectral Image Compression , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Valero Laparra,et al.  Regression Wavelet Analysis for Lossless Coding of Remote-Sensing Data , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Jarno Mielikäinen,et al.  Lossless Compression of Hyperspectral Images Using a Quantized Index to Lookup Tables , 2008, IEEE Geoscience and Remote Sensing Letters.

[7]  Fengchao Wang,et al.  Lossy hyperspectral image compression based on intra-band prediction and inter-band fractal encoding , 2016, Comput. Electr. Eng..

[8]  Giovanni Motta,et al.  Low-complexity lossless compression of hyperspectral imagery via linear prediction , 2005, IEEE Signal Processing Letters.

[9]  Da-Wen Sun,et al.  Hyperspectral imaging with multivariate analysis for technological parameters prediction and classification of muscle foods: A review. , 2017, Meat science.

[10]  Marcelo C. M. Teixeira,et al.  Discrete-Time Sliding Mode Control for Uncertain Networked System Subject to Time Delay , 2015 .

[11]  Shiping Zhu,et al.  Hybrid Prediction and Fractal Hyperspectral Image Compression , 2015 .

[12]  Jeffrey Scott Vitter,et al.  New Methods for Lossless Image Compression Using Arithmetic Coding , 1992, Inf. Process. Manag..

[13]  Hossam Faris,et al.  Training feedforward neural networks using multi-verse optimizer for binary classification problems , 2016, Applied Intelligence.

[14]  Hongda Shen,et al.  Predictive Lossless Compression of Regions of Interest in Hyperspectral Images With No-Data Regions , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Martin T. Hagan,et al.  Neural network design , 1995 .

[16]  Manoranjan Paul,et al.  Reflectance Prediction Modelling for Residual-Based Hyperspectral Image Coding , 2016, PloS one.

[17]  Luciano Alparone,et al.  Lossless Compression of Hyperspectral Images Using Multiband Lookup Tables , 2009, IEEE Signal Processing Letters.

[18]  Omaima N. Ahmad AL-Allaf,et al.  Fast Backpropagation Neural Network algorithm for reducing convergence time of BPNN image compression , 2011, ICIMU 2011 : Proceedings of the 5th international Conference on Information Technology & Multimedia.

[19]  Junwei Han,et al.  A Survey on Object Detection in Optical Remote Sensing Images , 2016, ArXiv.

[20]  Manoranjan Paul,et al.  Lossless Hyperspectral Image Compression Using Binary Tree Based Decomposition , 2016, 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[21]  N. Albert Singh,et al.  A Novel Compression Technique for Compound Images Using Parallel Lempel-Ziv-Welch Algorithm , 2014 .

[22]  Giovanni Motta.  Hyperspectral Data Compression , 2006 .

[23]  Bosoon Park,et al.  Hyperspectral Imaging Technology in Food and Agriculture , 2015 .