Research on Lossless Compression of Hyperspectral Images Based on Improved Deep Learning Algorithm

This study explores the utilization of Binary Embedded Zero Tree Wavelet Algorithms (BEZW) to compress hyperspectral images. The primary goal is to enhance the representation of spectral data while minimizing storage and transmission requirements. The BEZW algorithm employs wavelet transformations to leverage both spectral and spatial redundancies found in hyperspectral data cubes. Its embedded zero tree structure ensures efficient encoding of small coefficients with minimal overhead. The study evaluates the performance of the BEZW method utilizing various hyper-spectral datasets and compression settings, comparing it to other compression techniques. The results illustrate that the BEZW algorithm offers a promising approach to hyperspectral image compression, achieving competitive compression ratios while preserving spectral accuracy. This makes it a valuable option for applications where efficient hyperspectral data storage and transmission are crucial. The research contributes to the field of hyperspectral imaging by introducing an effective compression method that enhances data accessibility, simplifying the utilization of hyperspectral data in resource-constrained environments.

Integer-coefficient Discrete Wavelet Transformation (DWT) filters widely used in the literature are implemented and investigated as spectral decorrelator for on-board lossless hyperspectral image compression. As the performance of spectral decorrelation step has direct impact on the compression ratio (CR), it is important to employ the most convenient spectral decorrelator in terms of low computational complexity and high CR. Extensive tests using AVIRIS image data set are carried out and CRs corresponding to various subband decomposition levels are presented within a lossless hyperspectral compression framework. Results suggest that Cohen-Daubechies-Feauveau (CDF) 9/7 integer-coefficient wavelet transform with five levels of spectral subband decomposition would be an efficient spectral decorrelator for on-board lossless hyperspectral image compression.

Hyperspectral images are a widely used remote sensing technique. These images are three-dimensional data structures, where the x and y axes contain spatial information and the z-axis contains spectral information or image bands. Usually, these bands can reach the order of hundreds, generating a considerable amount of information. Due to storage limitations and communication bandwidth, the use of compression techniques becomes essential. For spatial applications, a standard commonly used in the literature is CCSDS 123, developed by the Consultative Committee for Space Data Systems, which describes the algorithm for lossless compression of hyperspectral images. In this context, we implemented the prediction stage of the CCSDS 123 algorithm in the Xilinx Zynq-7000 FPGA. The developed processor provides a good trade-off to meet real-time requirements at low-cost.

提出了一种基于聚类-单邻点、多波段预测-ç†µç¼–ç çš„é«˜å ‰è°±æ•°æ®æ— æŸåŽ‹ç¼©æ–¹æ³•ã€‚æ ¹æ®è°±å‘ç‰¹å¾,è¿›è¡Œé«˜å ‰è°±å›¾åƒçŸ¢é‡èšç±»ã€‚å¯¹å„ä¸ªåˆ†ç±»,采用单个空间位置邻点、多个波段作为预测数据,训练预测系数,进行三维预测。残差采用Golomb-Riceç¼–ç ã€‚å®žéªŒè¯å®žäº†ç®—æ³•çš„æœ‰æ•ˆæ€§ã€‚

While adaptive filtering has been widely used in predictive lossless compression of hyperspectral images, the prediction performance depends heavily on the filtering weights estimated in a step-by-step manner. Traditional filtering methods do not take into account the longer-term dependencies of the data to be predicted. Motivated by the effectiveness of recurrent neural networks in capturing data memory for time series prediction, we design LSTM (long short-term memory) networks that can learn the data dependencies indirectly from filter weight variations. We then use the trained networks to regulate the weights generated by conventional filtering schemes through a close-loop configuration. We compare the proposed method with two other memory-less algorithms, including the popular Least Mean Square (LMS) filtering method, as well as its variant based on the maximum correntropy criterion (MCC). Simulation results on two publicly available datasets show that the proposed LSTM based filtering method can achieve smaller prediction errors.

The data size of hyperspectral image is too large for storage and transmission, and it has become a bottleneck restricting its applications. So it is necessary to study a high efficiency compression method for hyperspectral image. Prediction encoding is easy to realize and has been studied widely in the hyperspectral image compression field. Fractal coding has the advantages of high compression ratio, resolution independence, and a fast decoding speed, but its application in the hyperspectral image compression field is not popular. In this paper, we propose a novel algorithm for hyperspectral image compression based on hybrid prediction and fractal. Intraband prediction is implemented to the first band and all the remaining bands are encoded by modified fractal coding algorithm. The proposed algorithm can effectively exploit the spectral correlation in hyperspectral image, since each range block is approximated by the domain block in the adjacent band, which is of the same size as the range block. Experimental results indicate that the proposed algorithm provides very promising performance at low bitrate. Compared to other algorithms, the encoding complexity is lower, the decoding quality has a great enhancement, and the PSNR can be increased by about 5 dB to 10 dB.

There has recently been a strong interest towards low-complexity approaches for hyperspectral image compression, also driven by the standardization activities in this area and by the new hyperspectral missions that have been deployed. This chapter overviews the state-of-the-art of lossless and near-lossless compression of hyperspectral images, with a particular focus on approaches that comply with the requirements typical of real-world mission, in terms of low complexity and memory usage, error resilience and hardware friendliness. In particular, a very simple lossless compression algorithm is described, which is based on block-by-block prediction and adaptive Golomb coding, can exploit optimal band ordering, and can be extended to near-lossless compression. We also describe the results obtained with a hardware implementation of the algorithm. The compression performance of this algorithm is close to the state-of-the-art, and its low degree of complexity and memory usage, along with the possibility to compress data in parallel, make it a very good candidate for onboard hyperspectral image compression.

Nonnegative tensor Tucker decomposition (NTD) in a transform domain (e.g., 2D-DWT, etc) has been used in the compression of hyper-spectral images because it can remove redundancies between spectrum bands and also exploit spatial correlations of each band. However, the use of a NTD has a very high computational cost. In this paper, we propose a low complexity NTD-based compression method of hyper-spectral images. This method is based on a pair-wise multilevel grouping approach for the NTD to overcome its high computational cost. The proposed method has a low complexity under a slight decrease of the coding performance compared to conventional NTD. We experimentally confirm this method, which indicates that this method has the less processing time and keeps a better coding performance than the case that the NTD is not used. The proposed approach has a potential application in the loss compression of hyper-spectral or multi-spectral images

The article considers the relevance of the development of lossless image compression and transmission algorithms and their application for creating transport video surveillance systems. A brief overview of lossless transport image compression methods is provided. We propose a method for compressing transport plots based on the pyramid-recursive method of splitting the source image into polygons of various shapes and sizes. We consider two new algorithms for implementing the proposed method that are fundamentally different from each other: with a transition to the spectral region and without a transition to the spectral region of the original signal to ensure lossless compression. The results of testing various well-known lossless compression algorithms are analyzed: series length, Huffman, and arithmetic encoding, and compared with the proposed algorithms. It is shown that the proposed algorithms are more efficient in terms of compression ratio (2—3 times) compared to the known ones, while the computational complexity increases approximately by more than 3-4 times.

An antidictionary is particularly useful for data compression, and on-line electrocardiogram (ECG) lossless compression algorithms using antidictionaries have been proposed. They work in real-time with constant memory and give better compression ratios than traditional lossless data compression algorithms, while they only deal with ECG data on a binary alphabet. This paper proposes on-line ECG lossless compression for a given data on a finite alphabet. The proposed algorithm gives not only better compression ratios than those algorithms but also uses less computational space than they do. Moreover, the proposed algorithm work in real-time. Its effectiveness is demonstrated by simulation results.

Paddy seed viability prediction based on feature fusion of color and hyperspectral image with multivariate analysis

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.

Hyperspectral image (HSI) classification remains a challenging problem due to unique characteristics of HSI data (such as numerous bands and strong correlations in the spectral and spatial domains) and small sample size. To address such concerns, we propose a novel spectral–spatial feature extraction method for HSI classification by employing graph embedding and deep learning (DL) models. Since the conventional graph cannot capture the complex manifold relationship of HSI data, and there exist the observations of within-class variation as well as the similarity between different classes in the spectral domain, we construct the supervised within-class/between-class hypergraph (SWBH) to extract the spectral features of HSI. Since it is difficult for DL models to learn representative features for HSI data when the labeled training samples are limited, we propose the random zero settings to newly generate a large amount of labeled HSI samples for the training of convolutional neural network (CNN). The designed sample expanded CNN (SECNN) is used to extract the HSI spatial features. Thus, the spectral–spatial features of HSI can be learned by integrating the features extracted from SWBH and SECNN, respectively. Experiments on three real HSI datasets demonstrate higher classification accuracy of the proposed SWBH–SECNN method.

Hyperspectral image compression has become increasingly important in data exploitation because of enormous data volumes and high redundancy provided by hundreds of contiguous spectral channels. Since a hyperspectral image can be viewed as a 3-dimensional (3D) image cube, many efforts have been devoted to extending 2D image compression techniques to perform 3D image compression on hyperspectral image cubes. Unfortunately, some major issues generally encountered in hyperspectral data exploitation at low or very low-bit rate compression, for example, subpixels and mixed pixels which do not occur in traditional pure pixel-based image compression are often overlooked in such a 2D-to-3D compression. Accordingly, a direct application of 2D-to-3D compression techniques to hyperspectral image cubes without taking precaution may result in significant loss of crucial spectral information provided by subtle substances such as small objects, anomalies during low bit-rate lossy compression. This paper takes a rather different view by investigating lossy hyperspectral compression from a perspective of exploring spectral information, referred to as exploitation-based lossy compression and further develops spectral/spatial hyperspectral image compression to effectively preserve crucial and vital spectral information of objects which are generally missed by commonly used mean-squared error (MSE) or signal-to-noise ratio (SNR)-based compression techniques when lossy compression is performed at low bit rates. In order to demonstrate advantages of the proposed spectral/spatial compression approach applications of subpixel target detection and mixed pixel analysis are used for experiments for performance evaluation.

We propose a novel, lossless compression algorithm, based on the 2D Discrete Fast Fourier Transform, to approximate the Algorithmic (Kolmogorov) Complexity of Elementary Cellular Automata. Fast Fourier transforms are widely used in image compression but their lossy nature exclude them as viable candidates for Kolmogorov Complexity approximations. For the first time, we present a way to adapt fourier transforms for lossless image compression. The proposed method has a very strong Pearsons correlation to existing complexity metrics and we further establish its consistency as a complexity metric by confirming its measurements never exceed the complexity of nothingness and randomness (representing the lower and upper limits of complexity). Surprisingly, many of the other methods tested fail this simple sanity check. A final symmetry-based test also demonstrates our method’s superiority over existing lossless compression metrics. All complexity metrics tested, as well as the code used to generate and augment the original dataset, can be found in our github repository: ECA complexity metrics1.