No-Reference Video Quality Assessment using novel hybrid features and two-stage hybrid regression for score level fusion

This paper presents a novel No-Reference Video Quality Assessment (NR-VQA) model that utilizes proposed 3D steerable wavelet transform-based Natural Video Statistics (NVS) features as well as human perceptual features. Additionally, we proposed a novel two-stage regression scheme that significantly improves the overall performance of quality estimation. In the first stage, transform-based NVS and human perceptual features are separately passed through the proposed hybrid regression scheme: Support Vector Regression (SVR) followed by Polynomial curve fitting. The two visual quality scores predicted from the first stage are then used as features for the similar second stage. This predicts the final quality scores of distorted videos by achieving score level fusion. Extensive experiments were conducted using five authentic and four synthetic distortion databases. Experimental results demonstrate that the proposed method outperforms other published state-of-the-art benchmark methods on synthetic distortion databases and is among the top performers on authentic distortion databases. The source code is available at https://github.com/anishVNIT/two-stage-vqa.     

Transition from random packing to stable state in a continuously avalanching granular flow

We investigate the transition evolution from the initial state with the random packing of the particles to the stable state in which successive avalanches exhibit consistent characteristics under the slumping regime. It is found that there exist three distinct stages in the transition evolution, considering the change of the volume fraction. The coordination number is almost unchanged during the transition evolution, which indicates the particle contact form is consistent in the three stages. The pause phenomena are discovered in some avalanches, and the probability of pause occurrence increases continuously in the three consecutive stages. We also explore the distribution of particles in the passive layer at the stable state. The particles in the middle region of the passive layer have the closest packing status, and the deeper the region is located, the later it reaches the stable state.     

WSN低功耗低时延路径式协同计算方法

针对云计算应用于无线传感器网络(Wireless Sensor Network,WSN)时延敏感型业务时存在的高传输时延问题,提出了一种WSN低功耗低时延路径式协同计算方法。该方法基于一种云雾网络架构开展研究,该架构利用汇聚节点组成雾计算层;在数据传输过程中基于雾计算层的计算能力分步骤完成任务计算,降低任务处理时延;由于汇聚节点计算能力较弱,时延降低将导致能耗增加,WSN工作寿命减短,为此提出能耗约束下的任务映射策略,并利用离散二进制粒子群优化(Binary Particle Swarm Optimization,BPSO)算法解决能耗约束下的时延优化问题。仿真结果表明,在相同的能耗约束下,对比其他算法,基于BPSO算法得出的映射方案能有效降低业务处理时延,满足时延敏感型业务的需求。     

Lean production system design for fishing net manufacturing using lean principles and simulation optimization

Value stream mapping (VSM) is a useful tool for describing the manufacturing state, especially for distinguishing between those activities that add value and those that do not. It can help in eliminating non-value activities and reducing the work in process (WIP) and thereby increase the service level. This research follows the guidelines for designing future state VSM. These guidelines consist of five factors which can be changed simply, without any investment. These five factors are (1) production unit; (2) pacemaker process; (3) number of batches; (4) production sequence; and (5) supermarket size. The five factors are applied to a fishing net manufacturing system. Using experimental design and a simulation optimizing tool, the five factors are optimized. The results show that the future state maps can increase service level and reduce WIP by at least 29.41% and 33.92% respectively. For the present study, the lean principles are innovatively adopted in solving a fishing net manufacturing system which is not a well-addressed problem in literature. In light of the promising empirical results, the proposed methodologies are also readily applicable to similar industries.     

A signal adaptive diffusion filter for video coding: Mathematical framework and complexity reductions

In this paper we combine video compression and modern image processing methods. We construct novel iterative filter methods for prediction signals based on Partial Differential Equation (PDE) based methods. The mathematical framework of the employed diffusion filter class is given and some desirable properties are stated. In particular, two types of diffusion filters are constructed: a uniform diffusion filter using a fixed filter mask and a signal adaptive diffusion filter that incorporates the structures of the underlying prediction signal. The latter has the advantage of not attenuating existing edges while the uniform filter is less complex. The filters are embedded into a software based on HEVC with additional QTBT (Quadtree plus Binary Tree) and MTT (Multi-Type-Tree) block structure. In this setting, several measures to reduce the coding complexity of the tool are introduced, discussed and tested thoroughly. The coding complexity is reduced by up to 70% while maintaining over 80% of the gain. Overall, the diffusion filter method achieves average bitrate savings of 2.27% for Random Access having an average encoder runtime complexity of 119% and 117% decoder runtime complexity. For individual test sequences, results of 7.36% for Random Access are accomplished.     

刀尖圆弧半径补偿对球面零件车削加工影响的分析

采用刀尖圆弧半径为0.4 mm的刀片,以0、0.4 mm、0.8 mm、1.2 mm为刀尖圆弧半径补偿值,得到球面曲率半径不同的四个试件,基于三丰C-3200测量仪对球面轮廓度进行测量,分析刀尖圆弧半径补偿对球面零件车削加工的影响。分析结果表明,在进行凸球面零件加工时,HNC-818A数控系统中的刀尖圆弧半径补偿功能有效,球面的曲率半径与刀尖圆弧半径补偿值的单调性一致。当刀尖圆弧半径补偿值线性变化时,球面的曲率半径呈非线性变化。当设定刀尖圆弧半径为真实值时,球面轮廓最为理想。在球面零件加工实践中,使用刀尖圆弧半径补偿功能,精加工采用可转位机夹车刀,通过试切法合理修改刀尖圆弧半径补偿值,可以提高球面零件的车削加工质量。     

Experimental investigation of unconfined spherical and cylindrical flame propagation in hydrogen-air mixtures

This paper presents results of experimental investigations on spherical and cylindrical flame propagation in pre-mixed H₂/air-mixtures in unconfined and semi-confined geometries. The experiments were performed in a facility consisting of two transparent solid walls with 1 m² area and four weak side walls made from thin plastic film. The gap size between the solid walls was varied stepwise from thin layer geometry (6 mm) to cube geometry (1 m). A wide range of H₂/air-mixtures with volumetric hydrogen concentrations from 10% to 45% H₂ was ignited between the transparent solid walls. The propagating flame front and its structure was observed with a large scale high speed shadow system. Results of spherical and cylindrical flame propagation up to a radius of 0.5 m were analyzed. The presented spherical burning velocity model is used to discuss the self-acceleration phenomena in unconfined and unobstructed pre-mixed H₂/air flames.     

Grain mapping to freeform surface for machining using parameter-based incremental tracking method

This paper presents a novel method for mapping a texture for machining onto a freeform surface. When a grain texture designed on a 2D plane is projected onto a freeform surface simply, the texture is distorted along the curvature of the surface in the projection direction. Therefore, a method is required to suppress this distortion. The algorithm proposed in this paper rapidly generates a point cloud that represents a texture with less distortion on a simply connected parametric surface. Specifically, four equations that express local geometry constraints instead of conventional parameterization methods are presented to reduce the distortion between adjacent points on the point cloud. Solving these equations can generate grain textures on freeform surfaces. This paper examines two grain images mapped to two freeform surfaces that were prepared as case studies to demonstrate the effectiveness of the proposed method.     

基于深度学习的视频跟踪研究进展综述

近年来深度学习迅猛发展，颠覆了语音识别、图像分类、文本理解等领域的算法设计思路。深度学习因其具备强大的特征提取能力，在图像识别领域的成绩尤为突出。然而深度学习与视频监控领域的结合并不多，由于深度模型具有多层网络结构，算法复杂度大，训练和更新模型时比较耗时，很难满足实时性要求。回顾了深度学习的发展史，介绍了最近10年来国内外深度学习主要模型，论述了基于深度学习的目标跟踪算法，指出了各算法的优缺点，最后对当前该领域存在的问题和发展前景进行了总结和展望。     

视频侦查中人像智能分析应用及算法优化

人像智能分析指的是对视频或录像中的人像进行结构化和可视化分析,对目标人物进行性别、年龄、发型等特征的智能识别,这项技术在视频侦查中有极高的应用价值。人像识别早期的算法是通过人工提取特征,通过学习低级视觉特征来针对不同属性进行分类学习,这种基于传统方法的模型表现常常不尽如人意。在计算机视觉领域,通过海量图像数据学习的神经网络比传统方法有更丰富的信息量和特征可以被提取。文章尝试通过深度学习技术训练神经网络模型对行人进行检测和识别,对于衣着不同的行人进行智能识别,具有更好的鲁棒性,提升了视频人像识别的准确率,拓展了人工智能技术在身份识别领域的应用。