Search

A huge advantage of the wavelet transform in image and video compression is its scalability. Wavelet-based coding of medical computed tomography (CT) data becomes more and more popular. While much effort has been spent on encoding of the wavelet coefficients, the extension of the transform by a compensation method as in video coding has not gained much attention so far. We will analyze two compensation methods for medical CT data and compare the characteristics of the displacement compensated wavelet transform with video data. We will show that for thorax CT data the transform coding gain can be improved by a factor of 2 and the quality of the lowpass band can be improved by 8 dB in terms of PSNR compared to the original transform without compensation.

Traditional video compression approaches build upon the hybrid coding framework with motion-compensated prediction and residual transform coding. In this paper, we propose the first end-to-end deep video compression framework to take advantage of both the classical compression architecture and the powerful non-linear representation ability of neural networks. Our framework employs pixel-wise motion information, which is learned from an optical flow network and further compressed by an auto-encoder network to save bits. The other compression components are also implemented by the well-designed networks for high efficiency. All the modules are jointly optimized by using the rate-distortion trade-off and can collaborate with each other. More importantly, the proposed deep video compression framework is very flexible and can be easily extended by using lightweight or advanced networks for higher speed or better efficiency. We also propose to introduce the adaptive quantization layer to reduce the number of parameters for variable bitrate coding. Comprehensive experimental results demonstrate the effectiveness of the proposed framework on the benchmark datasets.

In this article, a survey of the point cloud compression (PCC) methods by organizing them with respect to the data structure, coding representation space, and prediction strategies is presented. Two paramount families of approaches reported in the literature—the projection- and octree-based methods—are proven to be efficient for encoding dense and sparse point clouds, respectively. These approaches are the pillars on which the Moving Picture Experts Group Committee developed two PCC standards published as final international standards in 2020 and early 2021, respectively, under the names: video-based PCC and geometry-based PCC. After surveying the current approaches for PCC, the technologies underlying the two standards are described in detail from an encoder perspective, providing guidance for potential standard implementors. In addition, experiment evaluations in terms of compression performances for both solutions are provided.

This article introduces the ISO/IEC MPEG Immersive Video (MIV) standard, MPEG-I Part 12, which is undergoing standardization. The draft MIV standard provides support for viewing immersive volumetric content captured by multiple cameras with six degrees of freedom (6DoF) within a viewing space that is determined by the camera arrangement in the capture rig. The bitstream format and decoding processes of the draft specification along with aspects of the Test Model for Immersive Video (TMIV) reference software encoder, decoder, and renderer are described. The use cases, test conditions, quality assessment methods, and experimental results are provided. In the TMIV, multiple texture and geometry views are coded as atlases of patches using a legacy 2-D video codec, while optimizing for bitrate, pixel rate, and quality. The design of the bitstream format and decoder is based on the visual volumetric video-based coding (V3C) and video-based point cloud compression (V-PCC) standard, MPEG-I Part 5.

Proceedings of the IEEE 109(9), 1463-1493 (2021). doi:10.1109/JPROC.2020.3043399, Published by Institute of Electrical and Electronics Engineers, New York, NY [u.a.]

The file attached to this record is the author's final peer reviewed version. The Satisfied User Ratio (SUR) for a given distortion level is the fraction of subjects that cannot perceive a quality difference between the original image and its compressed version. By predicting the SUR, one can determine the highest distortion level which allows to save bit rate while guaranteeing a good visual quality. We propose the first method to predict the SUR for symmetrically and asymmetrically compressed stereoscopic images. Unlike SUR prediction techniques for 2D images and videos, our method exploits the properties of binocular vision. We first extract features that characterize image quality and image content. Then, we use gradient boosting decision trees to reduce the number of features and train a regression model that learns a mapping function from the features to the SUR values. Experimental results on the SIAT-JSSI and SIAT-JASI datasets show high SUR prediction accuracy for H.265 All-Intra and JPEG2000 symmetrically and asymmetrically compressed stereoscopic images.

The state-of-the-art 2D-based dynamic point cloud (DPC) compression algorithm is the video-based point cloud compression (V-PCC) developed by the Moving Pictures Experts Group (MPEG). It first projects the DPC patch by patch from 3D to 2D and organizes the projected patches into a video. The video is then efficiently compressed by High Efficiency Video Coding. However, there are many unoccupied pixels that may have a significant influence on the coding efficiency. These unoccupied pixels are currently padded using either the average of 4-neighbors for the geometry or the push-pull algorithm for the color attribute. While these algorithms are simple, the unoccupied pixels are not handled in the most efficient way. In this paper, we divide the unoccupied pixels into two groups: those that should be occupied and those that should not be occupied according to the occupancy map. We then design padding algorithms tailored to each group to improve the rate-distortion performance of the V-PCC reference software, for both the geometry and the color attribute. The first group is the unoccupied pixels that should be occupied according to the block-based occupancy map. We attempt to pad those pixels using the real points in the original DPC to improve the quality of the reconstructed DPC. Additionally, we attempt to maintain the smoothness of each block so as not to negatively influence the video compression efficiency. The second group is the unoccupied pixels that were correctly identified as unoccupied according to the block-based occupancy map. These pixels are useless for improving the reconstructed quality of the DPC. Therefore, we attempt to minimize the bit cost of these pixels without considering their reconstruction qualities. The bit cost is determined by the residue of these pixels obtained by subtracting the prediction pixels from the original pixels. Therefore, we propose padding the residue using the average residue of the occupied pixels in order to minimize the bit cost. The proposed algorithms are implemented in the V-PCC and the corresponding HEVC reference software. The experimental results show the proposed algorithms can bring significant bitrate savings compared with the V-PCC.

While traditional image compression algorithms take a full three-component color representation of an image as input, capturing of such images is done in many applications with Bayer CFA pattern sensors that provide only a single color information per sensor element and position. In order to avoid additional complexity at the encoder side, such CFA pattern images can be compressed directly without prior conversion to a full color image. In this paper, we describe a recent activity of the JPEG committee (ISO SC 29 WG 1) to develop such a compression algorithm in the framework of JPEG XS. It turns out that it is important to understand the ""development process"" from CFA patterns to full color images in order to optimize the image quality of such a compression algorithm, which we will also describe shortly. We introduce (1) a novel decorrelation step upfront processing (the so-called Star-Tetrix transform), along with (2) a pre-emphasis function to improve the compression efficiency of the subsequent compression algorithm (here, JPEG XS). Our experiments clearly indicate a gain over a RGB compression workflow in terms of complexity and quality (between 1.5dB and more than 4dB depending on the target bitrate). A comparison is also made with other state-of-the-art CFA compression techniques.

JPEG lossy image compression is a still image compression algorithm model that is currently widely used in major network media. However, it is unsatisfactory in the quality of compressed images at low bit rates. The objective of this paper is to improve the quality of compressed images and suppress blocking artifacts by improving the JPEG image compression model at low bit rates. First, the image texture adaptive non-uniform rectangular partition (ITANRP) algorithm is proposed which partitions the image into $8\times 8$ size image blocks with high texture complexity and $16\times 16$ size image blocks with low texture complexity. Then, a new transform coding based on the complete orthogonal U-system and all-phase digital filter (APDF) is proposed for coding image blocks with different sizes. Next, a flexible adaptive quantization scheme is designed to quantize image blocks with different sizes by considering the sensitivity of the human visual system (HVS) to different texture complexities. Finally, combining the above method with the JPEG model, a novel image compression algorithm model with low algorithm complexity is proposed to solve the problem in JPEG. The experimental results demonstrate that the performance of our algorithm model outperforms the JPEG image compression algorithms, the quality of the compressed image is greatly improved, and the blocking artifacts are also significantly suppressed.

For multidimensional data, Space-Filling Curves (SFCs) have been used to improve the execution time of spatial data queries. However, their effect on compression, when used to reorder the uncompressed values, is known to a lesser extent. We investigate the impact of three SFCs on Shuttle Radar Topographic Mission (SRTM) elevation data and Square-Kilometre Array telescope (SKA) radio-astronomy data: two types of datasets to which SFCs have not been extensively applied, within a compression context. This work contributes to the understanding of how such reorderings impact compression performance and affect different compression schemes and preprocessing techniques through their use. We show empirical results from combining eight common compression schemes, the Z-Order, Gray-Code, and Hilbert space-filling curves, and the bitwise preprocessing technique BitShuffle. The Hilbert Curve consistently outperforms the other orderings for the SRTM dataset though the mapping implementation incurs a significant speed penalty. However, the Z-Order and Gray-Code Curves are best for the SKA dataset. Through an analysis of the dataset autocorrelations, file-entropies, and block-entropies; we show that the SKA dataset’s dimensional bias is not exploited as much by the Hilbert Curve compared to the Z-Order and Gray-Code Curves. However, the Hilbert Curve is the most appropriate for the SRTM dataset as it can be modelled as isotropic and has a significantly higher level of local autocorrelation. BitShuffle is necessary to practically compress the SKA data, but does contribute to the compression performance of the SRTM dataset. These curves and BitShuffle are advantageous in reducing block-entropy values for such datasets.

The most widely used video encoders share a common hybrid coding framework that includes block-based motion estimation/compensation and block-based transform coding. Despite their high coding efficiency, the encoded videos often exhibit visually annoying artifacts, denoted as Perceivable Encoding Artifacts (PEAs), which significantly degrade the visual Quality-of-Experience (QoE) of end users. To monitor and improve visual QoE, it is crucial to develop subjective and objective measures that can identify and quantify various types of PEAs. In this work, we make the first attempt to build a large-scale subject-labeled database composed of H.265/HEVC compressed videos containing various PEAs. The database, namely the PEA265, includes 4 types of spatial PEAs ( i.e. blurring, blocking, ringing and color bleeding) and 2 types of temporal PEAs ( i.e. flickering and floating). Each containing at least 60,000 image or video patches with positive and negative labels. Based on the PEA265 database, we develop and optimize Convolutional Neural Networks (CNNs) to objectively recognize different types of PEAs. Experiments show that our architecture is capable of identifying the 6 types of PEAs with an accuracy over 86%. To further demonstrate its application, we explore the relationship between collected PEA intensities and subjective quality scores of compressed videos. A quality metric is consequently proposed with superior performance in terms of correlation to Mean Opinion Score (MOS) values. We believe that the PEA265 database and our findings will benefit the future development of video quality assessment methods and perceptually motivated video encoders.

Compression algorithms have been proposed with the technology advance. However, there are not objective analysis procedures to guide a future choice of an algorithm directed for the type of data in the system they are intended for. This paper introduces a statistical framework, based on the bootstrap method, to execute the analysis of compression algorithms using an objective comparison parameter as a criterion. A case study using the compression ratio as the parameter and file samples of 4 different types was analyzed. The proposed scheme allowed us to infer which algorithm is better to be used for each data type. RLE has proven more suitable to image, audio and video files with Huffman obtaining comparable performance. For text files, LZW has remarkably outperformed all other algorithms.

Computer generated holograms represent a novel digital media that with adequate processing tools and the advance of holographic display technologies will foster the development of true immersive video technologies applications. A digital hologram typically conveys a considerable amount of data making compression and image quality evaluation tools necessary for the development of practical applications. This paper proposes an objective evaluation of the performances of state-of-the-art compression techniques applied to digital holographic data. The experimental analysis takes into account several holographic images reconstructing the holograms from different perspectives and distances. The results of the exploratory study are reported, discussed and complemented with a statistical analysis of the hologram data under test, providing insights for computer-generated holography compression techniques design.

The ITU-T Video Coding Experts Group and the ISO/IEC Moving Picture Experts Group issued a Call for Proposals (CfP) on video compression with capability beyond HEVC in October 2017. The CfP considered three categories of content – Standard Dynamic Range, High Dynamic Range and Wide Colour Gamut (HDR/WCG), and 360° Omni-directional video. As a result of the CfP process, the development of a new video coding standard, named Versatile Video Coding (VVC), was initiated. The goal of this paper is to provide an overview of the CfP responses for the HDR/WCG category. The paper includes a summary of work leading to the development of the CfP, a presentation of the CfP results for the HDR/WCG category, and a description of the specific HDR/WCG technologies submitted to the CfP.

In this paper, we describe a video coding design that enables a higher coding efficiency than the HEVC standard. The proposed video codec follows the design of block-based hybrid video coding, but includes a number of advanced coding tools. A part of the incorporated advanced concepts was developed by the Joint Video Exploration Team, while others are newly proposed. The key aspects of these newly proposed tools are the following. A video frame is subdivided into rectangles of variable size using a binary partitioning with variable split ratios. Three new approaches for generating spatial intra prediction signals are supported: A line-wise application of conventional intra prediction modes, coupled with a mode-dependent processing order, a region-based template matching prediction method and intra prediction modes based on neural networks. For motion-compensated prediction, a multi-hypothesis mode with more than two motion hypotheses can be used. In transform coding, mode dependent combinations of primary and secondary transforms are applied. Moreover, scalar quantization is replaced by trellis-coded quantization and the entropy coding of the quantized transform coefficients is improved. The intra and inter prediction signals can be filtered using an edge-preserving diffusion filter or a non-linear DCT-based thresholding operation. The video codec includes an adaptive in-loop filter for which one of three classifiers can be chosen on a picture basis. We also incorporated an optional encoder control, which adjusts the quantization parameters based on a perceptually motivated distortion measure. In a random access scenario, our proposed video codec achieves luma BD-rate savings between 32.5% for HDR HLG UHD and 39.6% for SDR UHD over the HEVC (HM software) anchor for different categories of test sequences.

Deep learning-based image compressors are actively being explored in an effort to supersede conventional image compression algorithms, such as JPEG. Conventional and deep learning-based compression algorithms focus on minimizing image fidelity errors in the nonlinear standard RGB (sRGB) color space. However, for many computer vision tasks, the sensor's linear raw-RGB image is desirable. Recent work has shown that the original raw-RGB image can be reconstructed using only small amounts of metadata embedded inside the JPEG image [1] . However, [1] relied on the conventional JPEG encoding that is unaware of the raw-RGB reconstruction task. In this paper, we examine the ability of deep image compressors to be “aware” of the additional objective of raw reconstruction. Towards this goal, we describe a general framework that enables deep networks targeting image compression to jointly consider both image fidelity errors and raw reconstruction errors. We describe this approach in two scenarios: (1) the network is trained from scratch using our proposed joint loss, and (2) a network originally trained only for sRGB fidelity loss is later fine-tuned to incorporate our raw reconstruction loss. When compared to sRGB fidelity-only compression, our combined loss leads to appreciable improvements in PSNR of the raw reconstruction with only minor impact on sRGB fidelity as measured by MS-SSIM.

The important role played by the data compression is in reducing the storage space required, and ensuring bandwidth utilization in efficient manner and low transmission delays. Image compression is also a part of data compression. Images contain important data that is to be transmitted or stored. The compression must not degrade the quality of the image, and should be acceptable. This paper presents simple, low complexity image compression algorithm. Algorithm scans the image in a raster san manner in terms of 4X4 blocks. Compression is achieved by the diagonally situated pixels and indices their surrounding pixels of the block. The mages produced by proposed algorithm are high fidelity images at low PSNR values. The results are comparable with standard algorithm results. The reconstructed image quality is better than JPEG images at same PSNR.

Image compression is one of the potential techniques for image processing. However, the compression also takes a certain amount of time, and some algorithms are not adapted to all images. In order to improve the processing efficiency and performance, this paper studied the relation between image characteristics and Peak Signal to Noise Ratio (PSNR) to predict the compression performance. In this paper, we adopted JPEG2000 algorithm to compress, and PSNR to evaluate the image quality. The statistics of an image contains the values of mean, variance, entropy and others. Then, we drew the relation graph between each statistic calculated and PSNR, and found the statistic which is the most closely related to PSNR. Finally, we derived an explicit expression. Experimental results show that Image Activity Measure (IAM) has the closest relation with PSNR, and the expression has the average relative error of 2% - 3.0%. Meanwhile, it can be simplified by ensuring that the formula error is unchanged basically. Furthermore, we also used other images dataset for verifying the formula. Gray images all can be well predicted for JPEG2000 algorithm when Compression Ratio (CR) is 16. It indicates that a more accurate and simpler IAM-PSNR relation we had obtained. Therefore, we can predict the compression performance before compression so as to select the appropriate compression algorithm and to provide great convenience for subsequent processing.

Embedded wireless imaging systems based on wireless camera sensor network can be used to observe biological phenomena unobtrusively in various environmental monitoring applications. In our prior work, we have shown the feasibility and benefits of such a system through actual deployments. We have also shown that low-complexity data compression schemes can be employed to improve image transfer rate or to lower the energy costs of communication. In this paper, we extend upon our prior work and propose a scheme called as H–K compression , a simple lightweight image compression algorithm combining the ideas of Huffman coding and K-means clustering. Specifically, H–K compression applies K-means clustering for pixel color grouping and Huffman coding for the group color encoding, but combines the two schemes into one algorithm which can reduce the computational cost. Using 100 000 images collected from our pilot deployments at James Reserve, we study the applicability and impact of the proposed algorithm. Our results suggest that the cost of running the learning steps on an embedded sensor node may outweigh the benefit of compression, but offloading the learning can provide significant energy gains. Evaluations using the data set show that our proposed scheme compresses the data by $\sim$ 57% and reduces power usage by $\sim$ 43% when sending image updates from a bird nest periodically every 15 min.

The design of a Wavelet -based Imaging System for Space missions is discussed in this paper. Capturing images of interest in launch vehicles is a multidisciplinary area involving teams from various branches of engineering; however, this paper specifically focuses on the design of the space -qualified imaging system that can work at low bit rates. The features of the system, design of various parameters, compression algorithm and its parameter selection, tests carried out to make the system space worthy are explained. The system is being used in various missions of ISRO to capture multiple events of interest. Finally, this paper shows some examples of the successful application of this system to recent missions.

Future PolSAR missions are expected to collect vast quantities of data, which can significantly add to the storage cost of various geospatial cloud driven applications. Data compression techniques like those prescribed by the JPEG2000 (JP2) standard might help counteract this cost. However, it is important to measure the impact on target application performance due to these techniques. In this paper, the impact of JP2 and JPEG compression on classification performance of PolSAR data is studied and it has been found that compression has no significant impact on Deep Neural Network (DNN) classification performance.

Field Programmable Gate Arrays are increasingly becoming an integral part of modern embedded system designs because of their ease of implementation, flexibility and unparalleled processing power capability. Taking into consideration these capabilities, a compression algorithm has been implemented on an FPGA (Xilinx Spartan 3A 3400 Kit) while the decompression part has been carried out on a Personal Computer (PC). The transmission between FPGA and PC has been done through Ethernet interfacing. Decompressor has been designed in MATLAB to decompress the data acquired through FPGA while the compression algorithm used is based on JPEG. Three different images have been considered for the test case purposes. Likewise, three resolutions of each image have been used for compression in FPGA and subsequent decompression using MATLAB in PC. Multiple cores strategy has been incorporated in the FPGA to speed up the compression process. The pictorial representation of each decompressed image viz-a-viz original image has been carried out. The Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE) have been calculated for each set of resolution for comparing image compression quality. The graphical representation of Mean square Error for all resolutions of each image separately has been depicted.

Traditional video codecs follow the predictive coding architecture of motion-compensated prediction and residual transform coding. Inspired by recent advances in deep learning, we propose a new deep learning video compression architecture that does not require motion estimation, which is the most expensive component in traditional video codecs. Our network consists of three components: a Displacement Calculation Unit (DCU), a Displacement Compression Network (DCN), and a Frame Reconstruction Network (FRN). The DCU exploits displaced frame differences as motion information, thus removing the need for motion estimation found in hybrid codecs. DCN utilizes an RNN-based network to learn temporal dependencies between frames. In the FRN, a new version of the UNet model, called LSTM-UNet is proposed and utilized to learn space-time differential representations of the videos. Our experimental results show that our compression model, MOtionless VIdeo Codec (MOVI-Codec), learns how to efficiently compress videos without computing motion and outperforms the video coding standard H.264 and exceeds the performance of the modern global standard HEVC codec as measured by MS-SSIM, especially on higher resolution videos.

The subject of this chapter is to describe selected topics on contour extraction, approximation and compression in spatial domain. Contours are treated as important image structure required in many applications, for example in analysis of medical image, computer vision, robot guidance, pattern recognition etc. Contour compression plays important role in many practical tasks associated with contour and image processing. The main approach solving the problem of contour compression is based on polygonal approximation. In this chapter the traditional and new methods for contour approximation in spatial domain are presented. These methods are often much faster than the methods of compression based on transform coding. In order to extract the contours from the image some algorithms have been developed. The selected well known methods for contour extraction and edge detection as well as the new algorithms are also presented in this chapter. The author is grateful to his Ph.D. students A. Ukasha and B. Fituri for their contribution in preparation of this chapter. 1. Contour Analysis and Extraction Contours and line drawings have been an important area in image data processing. In many applications, e.g., weather maps and geometric shapes, it is necessary to store and transmit large amounts of contours and line drawings and process the information by computers. Several approaches have been used to extract and encode the boundary points of contours and line drawings. The extracted data is then used for further processing and applications. Contour approximation and compression are some of the processing operations performed on contours and has been considered by several authors. In encoding contours and line drawings, efficient data compression and good reconstruction are both usually required. Freeman proposed an eight-directi onal encoding scheme for contour lines. The proposed chain code is obtained by superimposing a rectangular grid on the curve and then quantizing the curve to the nearest one of the eight possible grid points. The chain encoding scheme represents contour lines by 3 bits/link, where a link is defined as one of the eight possible straight-line segments between two adjacent quantized points. Efforts have been made to improve the coding efficiency. Freeman proposed a chain difference coding scheme which assigned variable-length codewords to the difference between two consecutive links. This coding scheme represents contour lines by about 2 to 2.1 bits/link on average.

Data compression is the way of reducing the number of bits required to store and efficiently utilize bandwidth during the transmission of data over a network channel. Image compression is also having importance as images contain important binary data to represent as image and that is to be stored and transmitted. The compression of an image must not reduce the quality of the image except in some cases. This paper proposes a compression algorithm with low PSNR, high fidelity images. The algorithm alienates the input image as non-overlapping blocks of size 4*4. Compression is achieved by using diagonally situated pixels and other adjacent pixels of the blocks. The decompression uses a simple approach. The diagonally situated pixels and other adjacent pixels are used to reconstruct images in decompression phase. The proposed algorithm reconstructs images with high fidelity at lower Peak Signal to Noise Ratio (PSNR). The results of proposed algorithm are compared with JPEG. Results have shown that at same PSNR values, reconstructed image quality by the proposed algorithm is better than that of the JPEG algorithm.

In this paper, a flexible and adaptive block-wise image compression architecture with restoration network is proposed to improve the rate-distortion (R-D) performance of learned image compression. In contrast to existing learned compression algorithms which perform the image based transform coding, our approach splits the input image into non-overlapped blocks and compresses each block adaptively based on their local content characteristics. To reduce the artifacts caused by the block partitioning, block fusion network is subsequently proposed to overcome the drawbacks of block-wise independent coding. Further, quantization fine-tuning training process is proposed and utilized to reduce the difference of quantization operations between the training process and testing process. Experimental results show that the proposed network architecture has the ability to obtain significant coding gain compared with existing conventional compression standards including Versatile Video Coding (VVC) and achieves comparable R-D performance with state-of-the-art learned image codec using less parameters.

The need for better quality compressed images with the limited channel bandwidth in real-time data transmissions is the reason for which compression technique plays an important role in multimedia wireless communication and also enhancing the speed of communication. Transform based compressions are widely used owing to their higher compression rate in images. To have a better compression; increasing the probability of finding a character/symbol substantially which results in frequency spread reduction is proposed. Such a lossless transform is called as ‘Analytical Transform’ (AT). Proof behind this transform decreasing the entropy and allowing a simple compression algorithm to work more effectively is explained. ‘Analytical Transform’ is a sequential data transform aiding for superior compression. A comparative analysis of other sequential data compressors like Lempel and Ziv against Huffman coding in the combination of Analytical transform provides 1.3 to 1.8 times better compression.