Onboard Hyperspectral Image Compression Using Compressed Sensing and Deep Learning

Kumar, Saurabh; Chaudhuri, Subhasis; Banerjee, Biplab; Ali, Tofik

doi:10.1007/978-3-030-11012-3_3

Cited by 9 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fu et al 32 inferred the spatial redundancy by clustering, introduced an adaptive sparse representation corresponding to the obtained clusters, and eventually compressed the intermediate data by entropy coding. In recent work, Kumar et al 33 introduced a novel framework for onboard compression. The authors obtained a single coded snapshot from the band images, obtained a sparse representation, and compressed the data using multiple layers of perceptron architecture.…”

Section: Tensor Ring Decompositionmentioning

confidence: 99%

See 1 more Smart Citation

Unmixing aware compression of hyperspectral image by rank aware orthogonal parallel factorization decomposition

Das,

Ghosal

2023

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

.Efficient compression is pertinent for the convenient storage, transmission, and processing of modern high-resolution hyperspectral images (HSI). We propose a high-performance HSI compression method using library-based spectral unmixing and tensor decomposition. Unlike the existing approaches, our proposed work incorporates unmixing in the compression framework and achieves significantly higher compression performance with negligible loss. The proposed library-based unmixing method includes an index for accurate endmember number estimation, followed by exact library pruning and a sparsity regularized formulation with norm-smoothing to compute the abundance maps. As the spectral library is available at the reconstruction (decoder) side also; compressing the abundance maps is as good as compressing the original HSI data. Since the abundance constraints used for the unmixing indicate the correlation of the abundance maps, compressing all abundance maps seems to cause redundant computation. A metric using the image smoothness and information measures is used here to identify the abundance map hardest to compress and the remaining part is left uncompressed. Subsequently, the work compresses the abundance map tensor using orthogonal PARAFAC decomposition with optimal rank determination. The orthogonalization process ensures that the factors span independent subspaces and reduces redundancy, whereas the rank selection prevents noisy or insignificant components. Extensive experiments are carried out to demonstrate that the unmixing workflow leads to negligible loss due to accurate endmember number estimation, exact library pruning, and accurate physically meaningful sparse inversion. Comparative assessments of compression efficacy suggest that the proposed work corresponds to better compression performance and higher classification accuracy.

show abstract

Section: Tensor Ring Decompositionmentioning

confidence: 99%

“…inferred the spatial redundancy by clustering, introduced an adaptive sparse representation corresponding to the obtained clusters, and eventually compressed the intermediate data by entropy coding. In recent work, Kumar et al 33 . introduced a novel framework for onboard compression.…”

Section: Literature Survey and Overviewmentioning

confidence: 99%

Unmixing aware compression of hyperspectral image by rank aware orthogonal parallel factorization decomposition

Das,

Ghosal

2023

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

show abstract

“…Optimal quantization step size is assigned, which can help in efficient decompression separately. CSDL-JP2 67 is another state-of-the-art compressive sensing technique in which matrix of measurement code is used to generate a database for coded snapshots. Realtime compression is done by deciding on encoder from snapshot database.…”

Section: Compressive Sensingmentioning

confidence: 99%

“…Dictionary update and dictionary learning are the two algorithms used to minimize the loss function for application-specific compression. CSDL-JP2 67 categorized under compressive sensing technique is also an example of sparse representation algorithm that has very high computational complexity.…”

Section: Cnn-ntd 31mentioning

confidence: 99%

Comprehensive review of hyperspectral image compression algorithms

2020

View full text Add to dashboard Cite

Rapid advancement in the development of hyperspectral image analysis techniques has led to specialized hyperspectral missions. It results in the bulk transmission of hyperspectral images from sensors to analysis centers and finally to data centers. Storage of these large size images is a critical issue that is handled by compression techniques. This survey focuses on different hyperspectral image compression algorithms that have been classified into two broad categories based on eight internal and six external parameters. In addition, we identified research challenges and suggested future scope for each technique. The detailed classification used in this paper can categorize other compression algorithms and may help in selecting research objectives.

show abstract

“…[ 25 ] proposed an onboard CNN-based lossy compressor, where the neural network is pre-trained on other datasets in a ground-based setting. For lossless compression, deep neural networks [ 26 , 27 ] and recurrent neural networks (RNN) [ 28 ] have been proposed to compress hyperspectral data by appropriately pre-training the networks.…”

Section: Introductionmentioning

confidence: 99%

Spatially and Spectrally Concatenated Neural Networks for Efficient Lossless Compression of Hyperspectral Imagery

2020

View full text Add to dashboard Cite

To achieve efficient lossless compression of hyperspectral images, we design a concatenated neural network, which is capable of extracting both spatial and spectral correlations for accurate pixel value prediction. Unlike conventional neural network based methods in the literature, the proposed neural network functions as an adaptive filter, thereby eliminating the need for pre-training using decompressed data. To meet the demand for low-complexity onboard processing, we use a shallow network with only two hidden layers for efficient feature extraction and predictive filtering. Extensive simulations on commonly used hyperspectral datasets and the standard CCSDS test datasets show that the proposed approach attains significant improvements over several other state-of-the-art methods, including standard compressors such as ESA, CCSDS-122, and CCSDS-123.

show abstract

Onboard Hyperspectral Image Compression Using Compressed Sensing and Deep Learning

Cited by 9 publications

References 16 publications

Unmixing aware compression of hyperspectral image by rank aware orthogonal parallel factorization decomposition

Unmixing aware compression of hyperspectral image by rank aware orthogonal parallel factorization decomposition

Comprehensive review of hyperspectral image compression algorithms

Spatially and Spectrally Concatenated Neural Networks for Efficient Lossless Compression of Hyperspectral Imagery

Contact Info

Product

Resources

About