Lossless compression for hyperspectral image using deep recurrent neural networks

Lossless and Near-Lossless Compression Algorithms for Remotely Sensed Hyperspectral Images

Rapid and continuous advancements in remote sensing technology have resulted in finer resolutions and higher acquisition rates of hyperspectral images (HSIs). These developments have triggered a need for new processing techniques brought about by the confined power and constrained hardware resources aboard satellites. This article proposes two novel lossless and near-lossless compression methods, employing our recent seed generation and quadrature-based square rooting algorithms, respectively. The main advantage of the former method lies in its acceptable complexity utilizing simple arithmetic operations, making it suitable for real-time onboard compression. In addition, this near-lossless compressor could be incorporated for hard-to-compress images offering a stabilized reduction at nearly 40% with a maximum relative error of 0.33 and a maximum absolute error of 30. Our results also show that a lossless compression performance, in terms of compression ratio, of up to 2.6 is achieved when testing with hyperspectral images from the Corpus dataset. Further, an improvement in the compression rate over the state-of-the-art k2-raster technique is realized for most of these HSIs by all four variations of our proposed lossless compression method. In particular, a data reduction enhancement of up to 29.89% is realized when comparing their respective geometric mean values.

Recursive Least Squares for Near-Lossless Hyperspectral Data Compression

The hyperspectral image compression scheme is a trade-off between the limited hardware resources of the on-board platform and the ever-growing resolution of the optical instruments. Predictive coding attracts researchers due to its low computational complexity and moderate memory requirements. We propose a near-lossless prediction-based compression scheme that removes spatial and spectral redundant information, thereby significantly reducing the size of hyperspectral images. This scheme predicts the target pixel’s value via a linear combination of previous pixels. The weight matrix of the predictor is iteratively updated using a recursive least squares filter with a loop quantizer. The optimal number of bands for prediction was analyzed experimentally. The results indicate that the proposed scheme outperforms state-of-the-art compression methods in terms of the compression ratio and quality retrieval.

Adaptive Lossless Image Data Compression Method Inferring Data Entropy by Applying Deep Neural Network

When we compress a large amount of data, we face the problem of the time it takes to compress it. Moreover, we cannot predict how effective the compression performance will be. Therefore, we are not able to choose the best algorithm to compress the data to its minimum size. According to the Kolmogorov complexity, the compression performances of the algorithms implemented in the available compression programs in the system differ. Thus, it is impossible to deliberately select the best compression program before we try the compression operation. From this background, this paper proposes a method with a principal component analysis (PCA) and a deep neural network (DNN) to predict the entropy of data to be compressed. The method infers an appropriate compression program in the system for each data block of the input data and achieves a good compression ratio without trying to compress the entire amount of data at once. This paper especially focuses on lossless compression for image data, focusing on the image blocks. Through experimental evaluation, this paper shows the reasonable compression performance when the proposed method is applied rather than when a compression program randomly selected is applied to the entire dataset.