Human action recognition using multi-layer codebooks of key poses and atomic motions

Taking fully into consideration the fact that one human action can be intuitively considered as a sequence of key poses and atomic motions in a particular order, a human action recognition method using multi-layer codebooks of key poses and atomic motions is proposed in this paper. Inspired by the dynamics models of human joints, normalized relative orientations are computed as features for each limb of human body. In order to extract key poses and atomic motions precisely, feature sequences are segmented into pose feature segments and motion feature segments dynamically, based on the potential differences of feature sequences. Multi-layer codebooks of each human action are constructed with the key poses extracted from pose feature segments and the atomic motions extracted from motion feature segments associated with each two key poses. The multi-layer codebooks represent action patterns of each human action, which can be used to recognize human actions with the proposed pattern-matching method. Three classification methods are employed for action recognition based on the multi-layer codebooks. Two public action datasets, i.e., CAD-60 and MSRC-12 datasets, are used to demonstrate the advantages of the proposed method. The experimental results show that the proposed method can obtain a comparable or better performance compared with the state-of-the-art methods.     

One‐Pot Synthesis of Dealloyed AuNi Nanodendrite as a Bifunctional Electrocatalyst for Oxygen Reduction and Borohydride Oxidation Reaction

A novel one‐pot approach for synthesizing the dealloyed nanomaterials at room temperature is introduced for the first time. In such a synthetic strategy, applying modulated potentials effectively simplifies the traditional dealloying route, which usually requires additional corrosion process to dissolve nonprecious metals. The dealloyed AuNi nanodendrites (AuNi NDs) with tunable composition and uniformly elemental distribution are well developed by the one‐pot strategy. Impressively, the as‐synthesized AuNi NDs exhibit a higher electrochemically active area and definite improvements in electrocatalytic activity for oxygen reduction reaction (ORR) and borohydride oxidation reaction (BOR) compared to the commercial Pt/C. In particular, the AuNi NDs are 81 mV more positive in half‐wave potential and about 3.1 times higher in specific activity (at 0.85 V) for the ORR than Pt/C, together with excellent stability and methanol tolerance. The superior BOR activity is highly promising compared to the previously reported catalysts. The unique nanodendritic structure with Au‐rich surface and bimetallic electronic effect is the main factor to greatly enhance the bifunctional catalytic performance for the AuNi NDs. Furthermore, such a newly developed facile method is of great significance because it is one of the first examples to effectively engineer dealloyed bimetallic nanostructures via the practical and low‐cost route for electrocatalytic applications.     

Skeleton-Based Human Action Recognition via Screw Matrices

With the recent advent of low-cost acqui-sition depth cameras, extracting 3D body skeleton has be-come relatively easier, which significantly lighten many dif-ficulties in 2D videos including occlusions, shadows and background extraction, etc. Directly perceived features, for example points, lines and planes, can be easily ex-tracted from 3D videos such that we can employ rigid motions to represent skeletal motions in a geometric way. We apply screw matrices, acquired by using rotations and translations in 3D space, to model single and multi-body rigid motion. Since screw matrices are members of the special Euclidean group SE(3), an action can be repre-sented as a point on a Lie group, which is a differen-tiable manifold. Using Lie-algebraic properties of screw al-gebra, isomorphic to se(3), the classical algorithms of ma-chine learning in vector space can be expanded to man-ifold space. We evaluate our approached on three public 3D action datasets: MSR Action3D dataset, UCF Kinect dataset and Florence3D-Action Dataset. The experimental results show that our approaches either match or exceed state-of-the-art skeleton-based human action recognition approaches.     

Content adaptive video denoising based on human visual perception

In this paper, we propose content adaptive denoising in highly corrupted videos based on human visual perception. We introduce the human visual perception in video denoising to achieve good performance. In general, smooth regions corrupted by noise are much more annoying to human observers than complex regions. Moreover, human eyes are more interested in complex regions with image details and more sensitive to luminance than chrominance. Based on the human visual perception, we perform perceptual video denoising to effectively preserve image details and remove annoying noise. To successfully remove noise and recover the image details, we extend nonlocal mean filtering to the spatiotemporal domain. With the guidance of content adaptive segmentation and motion detection, we conduct content adaptive filtering in the YUV color space to consider context in images and obtain perceptually pleasant results. Extensive experiments on various video sequences demonstrate that the proposed method reconstructs natural-looking results even in highly corrupted images and achieves good performance in terms of both visual quality and quantitative measures.     

In-situ sonosynthesis of cobblestone-like ZnO nanoparticles on cotton/polyester fabric improving photo,bio and sonocatalytic activities along with low toxicity and enhanced mechanical properties

For the first time in this study, in-situ sonosynthesis and deposition of ZnO nanoparticles under ultrasound irradiation was used to prepare multifunctional cotton/polyester fabric. The process was carried out at 80 ^°C in ultrasonic bath and was free from final heating of fabrics to convert zinc hydroxide to zinc oxide nanoparticles. This was due to the physical and chemical effects of ultrasound promoting the involved reactions and facilitating the nucleation and growth of ZnO nanoparticles. Central composite design was also used to statistically analyze the process, optimizing the applied condition including zinc precursor concentration, pH and the effect of dispersing agent namely cetyltrimethylammonium bromide surfactant (CTAB). The treated samples were further characterized by X-ray diffraction (XRD), field emission scanning electron microscopy (FESEM) and energy-dispersive spectroscopy (EDX). Photocatalytic activities of the treated samples were assessed based on the ability of fabrics to degrade Methylene Blue dye stain under sunlight irradiation. The effect of synthesis parameters on photocatalytic activities (self-cleaning) was statistically optimized. Moreover, for evaluating the sonocatalytic efficiencies of the samples Reactive Blue 2 was applied and the activities were studied by visible spectroscopy. The cotton/polyester samples possessed multifunctional properties including self-cleaning, sonocatalytic, antibacterial, antifungal, low cytotoxicity and enhanced mechanical properties.     

触摸调光控制芯片的设计与测试

电力作为一种方便的能源广泛应用于我们生活的各个方面,于是电能的节能变得尤为重要。由于家用照明设计可以从控制方面实现节能,因此人们可以根据自己不同时间的不同需要来调节灯光的亮度来达到节约电能的目的。本文提出了一种应用于家用照明亮度的调节控制芯片的设计方案,首先分析顶层模块的功能,再将其功能分类细化,分配到不同的子模块去实现,利用CMOS电压比较器来实现了过零检测、系统时钟脉冲产生、触摸控制等操作,并通过仿真软件验证了设计模块功能的正确性,最后经流片测试芯片功能满足设计要求。     

Depth video spatial and temporal correlation enhancement algorithm based on just noticeable rendering distortion model

Spatial and temporal inconsistency of depth video deteriorates encoding efficiency in three dimensional video systems. A depth video processing algorithm based on human perception is presented. Firstly, a just noticeable rendering distortion (JNRD) model is formulated by combining the analyses of the influence of depth distortion on virtual view rendering with human visual perception characteristics. Then, depth video is processed based on the JNRD model from two aspects, spatial and temporal correlation enhancement. During the process of spatial correlation enhancement, depth video is segmented into edge, foreground, and background regions, and smoothened by Gaussian and mean filters. The operations of the temporal correlation enhancement include temporal–spatial transpose (TST), temporal smoothing filter and inverse TST. Finally, encoding and virtual view rendering experiments are conducted to evaluate the proposed algorithm. Experimental results show that the proposed algorithm can greatly reduce the bit rate while it maintains the quality of virtual view.     

基于支持向量回归的立体图像客观质量评价模型

立体图像质量评价是评价立体视频系统性能的有效途径,而如何利用人类视觉特性对立体图像质量进行有效评价是目前的研究难点。该文根据图像奇异值有较强稳定性的特点,结合立体图像的主观视觉特性,提出了一种基于支持向量回归(Support Vector Regression, SVR)的立体图像客观质量评价模型。该模型通过分析立体图像的视觉特性,提取左右图像的奇异值作为立体图像的特征信息,然后根据立体图像的不同失真类型情况对其特征进行融合,通过SVR预测得到立体图像质量的客观评价值。实验结果表明,采用该文提出的客观评价模型对立体数据测试库进行评价,Pearson线性相关系数值在0.93以上,Spearman等级相关系数值在0.94以上,均方根误差值接近6,异常值比率值为0.00%,符合人眼视觉特性,能够很好地预测人眼对立体图像的主观感知。     

Characterizing pairwise contact patterns in human contact networks

We use a counting process representation of the pairwise contact process to analyze pairwise contact patterns. Studying two real-world traces, we find that the pairwise contact patterns have three characteristics. First, human contact patterns are influenced by daily and weekly cycles of activity. Second short time intervals with intensive contact event (bursts) are separated by long periods with few contact events. Third, the pairwise contact process exhibits long range dependence. We introduce a Markov modulated Poisson process (MMPP) as a flexible model for pairwise contact process exhibiting both regular structure and irregular bursts of activity. Using standard statistical techniques, we demonstrate that the proposed model is consistent with the empirical data. Our work has significant implication for mobility modeling and performance analysis in human contact networks.     

基于JPEG2000的遥感图像感兴趣区域编码新算法及其VLSI设计

为解决空间遥感图像数据量及信道带宽之间的矛盾,该文提出一种基于JPEG2000的感兴趣区域(Region Of Interest, ROI)编码算法。主流的JPEG2000 ROI编码算法难以兼顾ROI质量和系统计算量,且在低码率编码时有完全丢失背景的隐患。该算法通过精确控制各子带中背景系数的精度,使ROI分配到更多码流。并引入了人眼视觉特性,使较少的背景码流产生尽量好的视觉效果。另外,根据该算法提出了针对矩形ROI的超大规模集成电路(VLSI)设计,此设计经过简单调整,亦可适用于主流的ROI编码算法。测试结果表明,该算法在ROI质量和重建图像视觉效果上均表现优异,且支持任意形状ROI编码,兼容JPEG2000协议。该VLSI设计仅使JPEG2000系统运行时间增加一个周期,具有极高的吞吐率,可满足实时处理要求。