Soft Compression for Lossless Image Coding Based on Shape Recognition

Soft compression is a lossless image compression method that is committed to eliminating coding redundancy and spatial redundancy simultaneously. To do so, it adopts shapes to encode an image. In this paper, we propose a compressible indicator function with regard to images, which gives a threshold of the average number of bits required to represent a location and can be used for illustrating the working principle. We investigate and analyze soft compression for binary image, gray image and multi-component image with specific algorithms and compressible indicator value. In terms of compression ratio, the soft compression algorithm outperforms the popular classical standards PNG and JPEG2000 in lossless image compression. It is expected that the bandwidth and storage space needed when transmitting and storing the same kind of images (such as medical images) can be greatly reduced with applying soft compression.

Few-shot Neural Human Performance Rendering from Sparse RGBD Videos

Recent neural rendering approaches for human activities achieve remarkable view synthesis results, but still rely on dense input views or dense training with all the capture frames, leading to deployment difficulty and inefficient training overload. However, existing advances will be ill-posed if the input is both spatially and temporally sparse. To fill this gap, in this paper we propose a few-shot neural human rendering approach (FNHR) from only sparse RGBD inputs, which exploits the temporal and spatial redundancy to generate photo-realistic free-view output of human activities. Our FNHR is trained only on the key-frames which expand the motion manifold in the input sequences. We introduce a two-branch neural blending to combine the neural point render and classical graphics texturing pipeline, which integrates reliable observations over sparse key-frames. Furthermore, we adopt a patch-based adversarial training process to make use of the local redundancy and avoids over-fitting to the key-frames, which generates fine-detailed rendering results. Extensive experiments demonstrate the effectiveness of our approach to generate high-quality free view-point results for challenging human performances under the sparse setting.

Investigating the Effects of a Combined Spatial and Spectral Dimensionality Reduction Approach for Aerial Hyperspectral Target Detection Applications

Target detection and classification is an important application of hyperspectral imaging in remote sensing. A wide range of algorithms for target detection in hyperspectral images have been developed in the last few decades. Given the nature of hyperspectral images, they exhibit large quantities of redundant information and are therefore compressible. Dimensionality reduction is an effective means of both compressing and denoising data. Although spectral dimensionality reduction is prevalent in hyperspectral target detection applications, the spatial redundancy of a scene is rarely exploited. By applying simple spatial masking techniques as a preprocessing step to disregard pixels of definite disinterest, the subsequent spectral dimensionality reduction process is simpler, less costly and more informative. This paper proposes a processing pipeline to compress hyperspectral images both spatially and spectrally before applying target detection algorithms to the resultant scene. The combination of several different spectral dimensionality reduction methods and target detection algorithms, within the proposed pipeline, are evaluated. We find that the Adaptive Cosine Estimator produces an improved F1 score and Matthews Correlation Coefficient when compared to unprocessed data. We also show that by using the proposed pipeline the data can be compressed by over 90% and target detection performance is maintained.

Filtration network: A frame sampling strategy via deep reinforcement learning for video captioning

Recently many methods use encoder-decoder framework for video captioning, aiming to translate short videos into natural language. These methods usually use equal interval frame sampling. However, lacking a good efficiency in sampling, it has a high temporal and spatial redundancy, resulting in unnecessary computation cost. In addition, the existing approaches simply splice different visual features on the fully connection layer. Therefore, features cannot be effectively utilized. In order to solve the defects, we proposed filtration network (FN) to select key frames, which is trained by deep reinforcement learning algorithm actor-double-critic. According to behavior psychology, the core idea of actor-double-critic is that the behavior of agent is determined by both the external environment and the internal personality. It avoids the phenomenon of unclear reward and sparse feedback in training because it gives steady feedback after each action. The key frames are sent to combine codec network (CCN) to generate sentences. The operation of feature combination in CCN make fusion of visual features by complex number representation to make good semantic modeling. Experiments and comparisons with other methods on two datasets (MSVD/MSR-VTT) show that our approach achieves better performance in terms of four metrics, BLEU-4, METEOR, ROUGE-L and CIDEr.

Design and Experimental Evaluation of the Proactive Transmission of Replicated Frames Mechanism over Time-Sensitive Networking

In recent years the Time-Sensitive Networking (TSN) Task Group (TG) has been working on proposing a series of standards to provide Ethernet with hard real-time guarantees, online management of the traffic and fault tolerance mechanisms. In this way the TG expects to create the network technology of future novel applications with real-time and reliability requirements. TSN proposes using spatial redundancy to increase the reliability of Ethernet networks, but using spatial redundancy to tolerate temporary faults is not a cost-effective solution. For this reason, we propose to use time redundancy to tolerate temporary faults in the links of TSN-based networks. Specifically, we have proposed the Proactive Transmission of Replicated Frames (PTRF) mechanism, which consists in transmitting several copies of each frame in a preventive manner. In this article we present for the first time a detailed description of the mechanism, with the three different approaches we have designed. We also present the implementation of PTRF in a real TSN prototype. Furthermore, we carry out a qualitative comparison of the different approaches of the mechanism and we experimentally evaluate the approaches of the mechanism in a quantitative manner from three perspectives: the end-to-end delay, the jitter and the bandwidth consumption.

A GAN-Based Video Intra Coding

Intra prediction is a vital part of the image/video coding framework, which is designed to remove spatial redundancy within a picture. Based on a set of predefined linear combinations, traditional intra prediction cannot cope with coding blocks with irregular textures. To tackle this drawback, in this article, we propose a Generative Adversarial Network (GAN)-based intra prediction approach to enhance intra prediction accuracy. Specifically, with the superior non-linear fitting ability, the well-trained generator of GAN acts as a mapping from the adjacent reconstructed signals to the prediction unit, implemented into both encoder and decoder. Simulation results show that for All-Intra configuration, our proposed algorithm achieves, on average, a 1.6% BD-rate cutback for luminance components compared with video coding reference software HM-16.15 and outperforms previous similar works.

Reliability-Aware Multipath Routing of Time-Triggered Traffic in Time-Sensitive Networks

With the development of industrial networks, the demands for strict timing requirements and high reliability in transmission become more essential, which promote the establishment of a Time-Sensitive Network (TSN). TSN is a set of standards with the intention of extending Ethernet for safety-critical and real-time applications. In general, frame replication is used to achieve fault-tolerance, while the increased load has a negative effect on the schedule synthesis phase. It is necessary to consider schedulability and reliability jointly. In this paper, a heuristic-based routing method is proposed to achieve fault tolerance by spatial redundancy for TSNs containing unreliable links. A cost function is presented to evaluate each routing set, and a heuristic algorithm is applied to find the solution with higher schedulability. Compared to the shortest path routing, our method can improve the reliability and the success rate of no-wait scheduling by 5–15% depending on the scale of topology.

Adaptive Prediction Methods for Medical Image/Video compression for Telemedicine Application

Due to rapid development of multimedia communication and advancement of image acquisition process, there is a crucial requirement of high storage and compression techniques to mitigate high data rate with limited bandwidth scenario for telemedicine application. Lossless compression is one of the challenging tasks in applications like medical, space, and aerial imaging field. Apart from achieving high compression ratio, in these mentioned applications there is a need to maintain the original imaging quality along with fast and adequate processing. Predictive coding was introduced to remove spatial redundancy. The accuracy of predictive coding is based on the choice of effective and adaptive predictor which is responsible for removing spatial redundancy. Medical images like computed tomography (CT) and magnetic resonance imaging (MRI) consume huge storage and utilize maximum available bandwidth. To overcome these inherent challenges, the authors have reviewed various adaptive predictors and it has been compared with existing JPEG and JPEG LS-based linear prediction technique for medical images.

On the Use of Motion Vectors for 2D and 3D Error Concealment in H.264/AVC Video

The fundamental principles of the coding/decoding H.264/AVC standard are introduced emphasizing the role of motion estimation and motion compensation (MC) in error concealment using intra- and inter-frame motion estimates, along with other features such as the integer transform, quantization options, entropy coding possibilities, deblocking filter, among other provisions. Efficient MC is one of the certain reasons for H.264/AVC superior performance compared to its antecedents. The H.264/AVC has selective intra-prediction and optimized inter-prediction methods to reduce temporal and spatial redundancy more efficiently. Motion compensation/prediction using variable block sizes and directional intra-prediction to choose the adequate modes help decide the best coding. Unfortunately, motion treatment is a computationally-demanding component of a video codec. The H.264/AVC standard has solved problems its predecessors faced when it comes to image quality and coding efficiency, but many of its advantages require an increase in computing complexity.