Search

Multispectral images, with their unique three-dimensional characteristics, require specialized spatial-spectral feature extraction modules to achieve superior compression results. Current end-to-end compression frameworks underperform compared to advanced coding algorithms, primarily due to insufficient spectral feature extraction at high bit rates and challenges in guiding entropy coding. To address these issues, this paper proposes the Mixture Autoregressive Spectral Attention Network (MARSA-Net), featuring two attention mechanisms: Coor-Spec and LD-CAM, and an autoregressive component. Our evaluation on real datasets from satellites demonstrates MARSA-Net's superiority over traditional algorithms, including H.266/VVC, underlining its potential in multispectral image compression. This research contributes to improved compression methods and extends our understanding of spectral feature extraction in multispectral imagery. [ABSTRACT FROM AUTHOR]

The advent of the information age and the continuous development of spectrum imaging technologies have both triggered an explosion of multispectral image information data. Hence, image data need to be compressed first no matter transmitting or storing information. This paper designs an end-to-end compression algorithm based on spectral–spatial domain feature leaning (SSDFL). SSDFL consists of dual branches: one to obtain spectral features by Bi-ConvLSTM, and the other for spatial feature extraction via residual multiscale depth-wise convolutions (RMDCs). The attention mechanism is conductive to ulteriorly fuse features. The encoder with SSDFL serves to extract important features from multispectral images and decrease their size to 1/8 of its original size. After decreasing dimensions of images, the quantizer turns the latent floating-point characteristics into integer data. The following phase utilizes lossless entropy coding to execute coding on the integer input and estimate the bitstream. The rate-distortion is added to the training process in order to jointly optimize the image bitstream and loss. The decoder is nearly symmetrical to the encoder to restore high-quality images. Two datasets from the WorldView-3 and Setinel-2 satellites are adopted in experiment with PSNR, MS-SSIM, SS, and MSA as evaluation indexes. Corresponding results prove that the performance of the proposed approach is superior to that of traditional compression algorithms 3D-SPIHT and JPEG2000. In addition, compared with deep learning compression methods CNN-based, ConvGRU-based and Partitioned, the suggested method still outperforms at various bitrates. [ABSTRACT FROM AUTHOR]

The availability of spectral library makes hyperspectral sparse unmixing an attractive unmixing scheme, and the powerful feature extraction capability of deep learning meets the requirements of estimating abundances with hundreds of channels in sparse unmixing. However, few related researches have been carried out. In this letter, we propose a window transformer convolutional autoencoder (WiTCAE) to address the sparse unmixing problem. In our method, a well-designed transformer encoder for hyperspectral images (HIS) is applied before convolutional neural network (CNN), aiming at exploring nonlocal information by a new attention mechanism called window-based pixel-level multihead self-attention (WP-MSA). Three consecutive CNN blocks focus on further joint spatial–spectral feature extraction and adjust the number of channels to the number of endmembers contained in the spectral library. Moreover, CNN establishes the connections among windows and smooths out the discontinuities caused by window partition. The decoder is a convolutional layer with a kernel size of 1, and its weights are fixed to a known spectral library. Comparative experiments on both simulated and real datasets confirm the superiority of our proposed network. [ABSTRACT FROM AUTHOR]

Recently, the rapid development of multispectral imaging technology has received great attention from many fields, which inevitably involves the image transmission and storage problem. To solve this issue, a novel end-to-end multispectral image compression method based on spectral–spatial feature partitioned extraction is proposed. The whole multispectral image compression framework is based on a convolutional neural network (CNN), whose innovation lies in the feature extraction module that is divided into two parallel parts, one is for spectral and the other is for spatial. Firstly, the spectral feature extraction module is used to extract spectral features independently, and the spatial feature extraction module is operated to obtain the separated spatial features. After feature extraction, the spectral and spatial features are fused element-by-element, followed by downsampling, which can reduce the size of the feature maps. Then, the data are converted to bit-stream through quantization and lossless entropy encoding. To make the data more compact, a rate-distortion optimizer is added to the network. The decoder is a relatively inverse process of the encoder. For comparison, the proposed method is tested along with JPEG2000, 3D-SPIHT and ResConv, another CNN-based algorithm on datasets from Landsat-8 and WorldView-3 satellites. The result shows the proposed algorithm outperforms other methods at the same bit rate. [ABSTRACT FROM AUTHOR]

Multispectral image compression can considerably reduce the volume of data and promote their application. However, conventional single-scale compression schemes, such as JPEG2000 and three-dimensional set partitioning in hierarchical tree (3D-SPIHT), do not accurately preserve the features of images due to the complex features of multispectral images. A compression framework based on adaptive multiscale feature extraction with a convolutional neural network is proposed. First, an adaptive multiscale feature extraction module, which is the basic component of the compression framework, is designed to extract the multiscale spatial–spectral features of the multispectral images and adaptively adjust the weights of the features according to the content of the images. Second, the encoder, which is composed of multiscale feature extraction modules, extracts the multiscale spatial–spectral features of the multispectral images, and the extracted features are quantized and encoded by the quantizer and the entropy coder to generate a compressed bitstream. Third, the decoder, which is structurally similar to the encoder, is utilized to recover the images. The rate-distortion optimizer is embedded in the encoder to control the trade-off between the rate loss and the distortion. The results of these experiments on multispectral images of the Landsat 8 satellite and the WorldView-3 satellite validate the better performance of our compression framework compared with the performances of conventional schemes, including JPEG2000 and 3D-SPIHT. In order to further verify the effectiveness of multiscale features, the framework is compared with a single-scale compression algorithm based on deep learning, the experimental results validate that the performance of the single-scale compression algorithm superior to the conventional schemes but inferior to our multiscale algorithm, which indicates that the multiscale features can significantly improve the performance of the compression algorithm. [ABSTRACT FROM AUTHOR]