Multi-Level Fusion Net for hand pose estimation in hand-object interaction

This work is about solving a challenging problem of estimating the full 3D hand pose when a hand interacts with an unknown object. Compared to isolated single hand pose estimation, occlusion and interference induced by the manipulated object and the clutter background bring more difficulties for this task. Our proposed Multi-Level Fusion Net focuses on extracting more effective features to overcome these disadvantages by multi-level fusion design with a new end-to-end Convolutional Neural Network (CNN) framework. It takes cropped RGBD data from a single RGBD camera at free viewpoint as input without requiring additional hand–object pre-segmentation and object or hand pre-modeling. Through extensive evaluations on public hand–object interaction dataset, we demonstrate the state-of-the-art performance of our method.     

基于CNN的人体姿态识别

姿态识别是人机交互中重要的研究课题之一，随着机器学习与神经网络的发展，研究的方式和成果趋于多样化，姿态识别的应用价值也日趋广泛。本文通过构建卷积神经网络模型，该模型共有11层，在对采样的数据集中5种人体姿态进行卷积与池化操作，最后进入全连接层进行分类，从而完成对数据集的训练和识别。结果显示，相较于机器学习方法，该模型的识别性能更加优秀，且免去了复杂的特征提取方式设计，让网络自身提取特征进行识别分类，效果更好。     

Learning a Deep Predictive Coding Network for a Semi-Supervised 3D-Hand Pose Estimation

In this paper we present a CNN based approach for a real time 3D-hand pose estimation from the depth sequence. Prior discriminative approaches have achieved remarkable success but are facing two main challenges: Firstly, the methods are fully supervised hence require large numbers of annotated training data to extract the dynamic information from a hand representation. Secondly, unreliable hand detectors based on strong assumptions or a weak detector which often fail in several situations like complex environment and multiple hands. In contrast to these methods, this paper presents an approach that can be considered as semi-supervised by performing predictive coding of image sequences of hand poses in order to capture latent features underlying a given image without supervision. The hand is modelled using a novel latent tree dependency model (LDTM) which transforms internal joint location to an explicit representation. Then the modeled hand topology is integrated with the pose estimator using data dependent method to jointly learn latent variables of the posterior pose appearance and the pose configuration respectively. Finally, an unsupervised error term which is a part of the recurrent architecture ensures smooth estimations of the final pose. Experiments on three challenging public datasets, ICVL, MSRA, and NYU demonstrate the significant performance of the proposed method which is comparable or better than state-of-the-art approaches.      

任意角带式输送机转弯装置应用研究

煤炭运输线路出现变向转弯时，通过多台传统带式输送机搭接实现输送，存在设备投资大、运输系统复杂、人员需求多等问题。介绍了任意角带式输送机转弯装置的工作原理、结构组成和特点，任意角带式输送机转弯装置由转向模块、改向模块、受料模块及其他辅助装置组成，当巷道转弯角度变化后，仅需要调节转向和改向滚筒即可实现带式输送机转向。该设备结构新颖、承载力大、运转安全可靠，可实现对带式输送机防逆转、制动，克服了转向运行时胶带的滑移和受力不均等问题，实现了减人提效，同时，安装时不需要开掘机电设备硐室，减少了巷道工程量，具有广阔的推广前景。     

Mixed convective heat transfer enhancement in a ventilated cavity by flow modulation via rotating plate

The present study numerically explores the mixed convection phenomena in a differentially heated ventilated square cavity with active flow modulation via a rotating plate. Forced convection flow in the cavity is attained by maintaining external fluid flow through an opening at the bottom of the left cavity wall while leaving it through another opening at the right cavity wall. A counter-clockwise rotating plate at the center of the cavity acts as an active flow modulator. Moving mesh approach is used for the rotation of the plate and the numerical solution is achieved using arbitrary Lagrangian-Eulerian finite element formulation with a quadrilateral discretization scheme. Transient parametric simulations have been performed for various frequency of the rotating plate for a fixed Reynolds number (Re) of 100 based on maximum inlet flow velocity while the Richardson number (Ri) is maintained at unity. Heat transfer performance has been evaluated in terms of spatially averaged Nusselt number and time-averaged Nusselt number along the heated wall. Power spectrum analysis in the frequency domain obtained from the fast Fourier transform analysis indicates that thermal frequency and plate frequency start to deviate from each other at higher values of velocity ratio (>4).     

浅谈市政工程施工测量放线程序化

将道路工程平面上直线段 ,圆曲线段 ,缓和曲线段内任意一点的坐标和高程 ,同附近控制点 (测站点 )的坐标和高程编制成计算机操作程序 ,实现施工区域内任意一点测量放线程序化     

双分支特征融合网络的步态识别算法

目的 在步态识别算法中,基于外观的方法准确率高且易于实施,但对外观变化敏感;基于模型的方法对外观变化更加鲁棒,但建模困难且准确率较低。为了使步态识别算法在获得高准确率的同时对外观变化具有更好的鲁棒性,提出了一种双分支网络融合外观特征和姿态特征,以结合两种方法的优点。方法 双分支网络模型包含外观和姿态两条分支,外观分支采用GaitSet网络从轮廓图像中提取外观特征;姿态分支采用5层卷积网络从姿态骨架中提取姿态特征。在此基础上构建特征融合模块,融合外观特征和姿态特征,并引入通道注意力机制实现任意尺寸的特征融合,设计的模块结构使其能够在融合过程中抑制特征中的噪声。最后将融合后的步态特征应用于识别行人身份。结果 实验在CASIA-B （Institute of Automation,Chinese Academy of Sciences,Gait Dataset B）数据集上通过跨视角和不同行走状态两种实验设置与目前主流的步态识别算法进行对比,并以Rank-1准确率作为评价指标。在跨视角实验设置的MT （medium-sample training）划分中,该算法在3种行走状态下的准确率分别为93.4%、84.8%和70.9%,相比性能第2的算法分别提升了1.4%、0.5%和8.4%;在不同行走状态实验设置中,该算法在两种行走状态下的准确率分别为94.9%和90.0%,获得了最佳性能。结论 在能够同时获取外观数据和姿态数据的场景下,该算法能够有效地融合外观信息和姿态信息,在获得更丰富的步态特征的同时降低了外观变化对步态特征的影响,提高了步态识别的性能。     

一种多路压电驱动控制系统的研制及实验研究

针对粉体微输送的基本要求,提出一种基于DDS技术的多路压电控制系统的设计方案,系统包括了波形存储模块、基准频率产生模块、基准电压设置模块以及D/A输出模块等。系统可以实现多路信号的独立控制和输出,电压范围为0~100 V,频率范围为0~256 Hz,最后以羟基磷灰石和钛粉为例,进行了多路粉体微输送实验,结果表明所设计的系统完全满足多种粉体微输送的要求,并且具有非常高的稳定性和可靠性。     

200 MHz带宽基带信号发生器的设计与实现

介绍了基于FPGA的基带信号发生器设计方案,主要叙述了成型滤波以及任意重采样内插比等关键技术。该基带信号发生器不仅实现了标准数字调制格式的基带信号发生,而且通过FPGA内部的并行架构设计,实现了500 MHz的高速数据速率,I/Q带宽达到200 MHz。将其应用于矢量信号发生器中,既实现了PSK、ASK、FSK、MSK、QAM等标准数字调制格式的矢量信号,又实现了400 MHz矢量调制带宽。经过测试,在4 M码元速率的情况下,QPSK和512QAM调制格式的EVM分别达到0.7%和1.0%;400 MHz带宽的矢量调制信号频响小于1 dB。