Learning-based JNCD prediction for quality-wise perceptual quantization in HEVC

In visual perception, human only perceive discrete-scale quality levels over a wide range of coding bitrate. More clearly, the videos compressed with a series of quantization parameters (QPs) only have limited perceived quality levels. In this paper, perceptual quantization is transformed into the problem of how to determine the just perceived QP for each quality level, and a just noticeable coding distortion (JNCD) based perceptual quantization scheme is proposed. Specifically, multiple visual masking effects are analyzed and a linear regression (LR) based JNCD model is proposed to predict JNCD thresholds for all quality levels at first. According to the JNCD prediction model, the frame-level perceptual QPs for all quality levels are then derived on the premise of that coding distortions are infinitely close to the predicted JNCD thresholds. Based on the predicted frame-level perceptual QPs, the perceived QPs of all quality levels for each coding unit (CU) are finally determined according to a perceptual modulation function. Experimental results show that the proposed quality-wise perceptual quantization scheme is superior to the existing perceptual video coding algorithms significantly, i.e., the proposed perceptual quantization could save more bitrate with better quality.     

Optimized video compression with residual split attention and swin-block artifact contraction

Research in video compression has seen significant advancement in the last several years. However, the existing deep learning-based algorithms continue to be plagued by erroneous motion compression and ineffective motion compensation architectures, resulting in compression errors with a lower rate–distortion trade-off. To overcome these challenges, we present an end-to-end purely deep learning-based video compression method through a set of primary operations (e.g., motion estimation, motion compression, motion compensation, residual compression, and artifact contraction) differently. A deep residual attention split (DRAS) block is introduced for motion compression networks to pay more attention to certain image regions to create more effective features for the decoder while boosting the rate–distortion optimization (RDO) efficiency. A channel residual block (CRB) is proposed in motion compensation to yield a more accurate predicted frame, potentially improving the residual frame. To mitigate the compression errors, an artifact contraction module (ACM) by residual swin convolution UNet block is included in this model to improve the reconstruction quality. To improve the final frame, a buffer is added to fine-tune the previous reference frames. These modules combine with a loss function by assessing the trade-off and enhancing the decoded video quality. A comprehensive ablation study demonstrates the effectiveness of the proposed blocks and modules for video compression. Experimental results show the competitive performance of the proposed method on four benchmark datasets.     

Multi-level rate-constrained successive elimination algorithm tailored to suboptimal motion estimation in HEVC

In the context of motion estimation for video coding, successive elimination algorithms (SEAs) significantly reduce the number of candidates evaluated during motion estimation without altering the resulting optimal motion vector. Nevertheless, SEA is often only used in conjunction with exhaustive search algorithms (e.g., full search). In this paper, we combine the multi-level successive elimination algorithm (ML-SEA) and the rate-constrained successive elimination algorithm (RCSEA) and show that they can be advantageously applied to suboptimal search algorithms. We demonstrate that the savings brought about by the new multi-level RCSEA (ML-RCSEA) outweigh the pre-computational costs of this approach for the Test Zonal (TZ) Search algorithm found in the HM reference encoder. We propose a novel multi-level composition pattern for performing RCSEA on an asymmetric partitioning. We introduce a double-check mechanism for RCSEA, and show that on average, it avoids computing 71% of motion vector (MV) costs. We also apply the proposed ML-RCSEA to bi-predictive refinement search and leverage a cost-based search ordering to remove 56% of error metric computations, on average. When compared to the HM reference encoder, our experiments show that the proposed solution reduces the TZ Search time by approximately 45%, contributing to an average encoding time reduction of about 7%, without increasing the Bjøntegaard delta rate (BD-Rate).     

Video object tracking and segmentation with box annotation

This paper presents a two-stage approach, track and then segment, to perform semi-supervised video object segmentation (VOS) with only bounding box annotations. The proposed reverse optimization for VOS (ROVOS) which leverages a fully convolutional Siamese network performs tracking and segmentation in the tracker. The segmentation cues are able to reversely optimize the location of the tracker and the object segmentation masks are produced by the two-branch system online. The experimental results on DAVIS 2016 and DAVIS 2017 demonstrate significant improvements of the proposed algorithm over the state-of-the-art methods.     

命名数据网络体系架构的应用与发展

命名数据网络（Named Data Networking,NDN）是一种以信息为中心的新型网络架构,因采用了独特的内容命名法、缓存机制和智能转发策略而受到广泛关注。首先介绍了NDN的基本原理、关键技术以及研究现状,并与TCP/IP架构对比分析了其性能优势;然后总结了NDN在车载自组织网（Vehicular Ad Hoc Network,VANET）、远程视频会议系统、大数据处理分析中的典型应用及研究现状;最后围绕实际应用指出了该技术的不足,并分析预测了其未来应用趋势。NDN对于解决互联网设计中日益凸显的安全性、移动性、可扩展性等方面的问题具有显著优势。     

电视节目移动编审系统设计

移动编审系统是传统节目编排的重要补充手段,满足了频道快速编排和移动办公的业务需求。本文介绍移动编审系统的应用场景、功能模块设计、后台支撑平台设计、后台应用设计以及接口设计。     

Motion vector modification distortion analysis-based payload allocation for video steganography

Video steganography forms a covert communication channel by data embedding in cover elements. To consider inter-frame mutual embedding impacts, this paper proposes a payload allocation strategy in video steganography based on motion vector modification distortion analysis. Firstly, the motion vector modification distortion caused by data embedding is analyzed. Then, a rate–distortion model reflecting the residue deviation propagation in successive inter-coded frames is derived. According to this model, the residue deviation propagation weight of each inter-coded frame can be computed. Finally, an inter-frame payload allocation strategy is designed in order to restrain the residue deviation propagation. Experimental results demonstrate that the proposed payload allocation strategy can enhance existing motion vector-based video steganographic methods in terms of undetectability and video coding performance. Besides, the lower computational complexity can be achieved.     

Multiview video summarization using video partitioning and clustering

Multiview video summarization plays a crucial role in abstracting essential information form multiple videos of the same location and time. In this paper, we propose a new approach for the multiview summarization. The proposed approach uses the BIRCH clustering algorithm for the first time on the initial set of frames to get rid of the static and redundant. The work presents a new approach for shot boundary detection using frame similarity measures Jaccard and Dice. The algorithm performs effectively synchronized merging of keyframes from all camera-views to obtain the final summary. Extensive experimentation conducted on various datasets suggests that the proposed approach significantly outperforms most of the existing video summarization approaches. To state a few, a 1.5% improvement on video length reduction, 24.28% improvement in compression ratio, and 6.4% improvement in quality assessment ratio is observed on the lobby dataset.     

Distance based kernels for video tensors on product of Riemannian matrix manifolds

In this paper, we explore the inherent geometry of video tensors by modeling them as points in product of Riemannian matrix manifolds. A video tensor is decomposed into three modes (factors) using matrix unfolding operation and each mode is represented as a point in a product space of Grassmannian and symmetric positive definite (SPD) matrix manifold. Hence a video is represented as a point in the Cartesian product of three such product spaces. Being a manifold valued (non-Euclidean) representation, application of several state-of-the-art Euclidean machine learning algorithms lead to inferior results. To overcome this, we propose positive definite kernels which map the points from product manifold space to Hilbert space. The proposed kernel functions implicitly make use of geodesic distance on product manifold to obtain a similarity measure and generate a kernel-gram matrix. In addition, we generate a discriminative feature representation for each manifold valued point using kernel-gram matrix diagonalization. Classification is performed in a sparse framework. The proposed methodology is tested over three publicly available datasets for hand gesture, traffic signal and sign language recognition. Experimentation performed over these datasets show that the proposed methodology is powerful in terms of classification accuracy in comparison with the state-of-the-art methods.     

Long-term rate control for concurrent multipath real-time video transmission in heterogeneous wireless networks

Concurrent multipath transmission provides an effective solution for streaming high-quality mobile videos in heterogeneous wireless networks. Rate control is commonly adopted in multimedia communication systems to fully utilize the available network bandwidth. This paper proposes a novel rate control for concurrent multipath video transmission. The existing rate control algorithms mainly adapt bit rate in the short-term pattern, i.e., without considering the long-term video transmission quality. We propose a long-term rate control scheme that takes into account the status of both the transmission buffer and video frames. First, a mathematical model is developed to formulate the non-convex problem of long-term quality maximization. Second, we develop a dynamic programming solution for online encoding bit rate control based on buffer status. The performance evaluation is conducted in a real test bed over LTE and Wi-Fi networks. Experimental results demonstrate that the proposed long-term rate control scheme achieves appreciable improvements over the short-term rate control schemes in terms of video quality and delay performance.