基于YCbCr肤色模型改进算法及区域特征的人脸检测研究

针对当前人脸检测的研究现状与难题,采用改进的YCbCr椭圆聚类肤色模型进行肤色区域提取,根据肤色在YCb’Cr’空间的分布,对于亮度小于80的非肤色像素点会误判为肤色点,则缩小椭圆聚类;对于亮度大于230的肤色像素点会误判为非肤色点,则扩大椭圆聚类,有效避免了在高亮度区域和亮度较低的区域中的肤色点误判问题。接着利用人脸的几何特征,对二值化图中的目标区域进行比例、大小结构的分析,排除不可能的人脸区域,并基于肤色和位置进行区域优化,将处理后的结果作为候选人脸区域输出。     

堆积体内部裂隙对降雨入渗的影响

降雨条件下滑坡体稳定性与裂隙诱发入渗密切相关。为了探究裂隙发育对堆积体降雨入渗的影响,以澜沧江某巨型堆积体坡表发育的裂隙现象为出发点,设计了均质堆积体和主-次裂隙堆积体2种模型。通过室内物理模拟试验及数值分析,并结合土体中的含水率、基质吸力、湿润锋迁移速度及深度的变化趋势可得出以下结论:裂隙型堆积体在降雨1 h和观测23 h的整个时间段内,其湿润锋迁移变化趋势可归纳为入渗加速→峰值→入渗减速→趋向于0;裂隙的存在为雨水入渗提供了有利的通道,雨水可到达土体深部,形成暂态饱和区,随降雨结束又逐渐消散;降雨在裂隙型发育的堆积体中的入渗过程可分为4个阶段,即前期完全入渗、裂隙下方强烈入渗、补偿加速入渗及水平侧渗。研究结果可为后续滑坡复活机理和稳定性评价提供参考。     

500kV变压器油色谱在线监测装置故障处理

在我国的电力发展过程中,变压器对输电系统具有举足轻重的作用,因此及时发现变压器潜伏性故障对于变压器的正常运行显得尤为重要。变压器油色谱在线监测装置就可以及时发现变压器本体内部存在的潜在故障,对变压器的安全运行起到很好的监视作用。但前提是油色谱在线监测装置运行及数据正常,才能正确分析变压器存在的故障。对油色谱在线监测装置运行过程中出现的故障现象进行描述,针对出现的现象进行深入分析,有效避免主变事故的发生,最终保证变压器长期安全稳定运行。     

CoGCN: Combining co‐attention with graph convolutional network for entity linking with knowledge graphs

Entity linking is a fundamental task in natural language processing. The task of entity linking with knowledge graphs aims at linking mentions in text to their correct entities in a knowledge graph like DBpedia or YAGO2. Most of existing methods rely on hand‐designed features to model the contexts of mentions and entities, which are sparse and hard to calibrate. In this paper, we present a neural model that first combines co‐attention mechanism with graph convolutional network for entity linking with knowledge graphs, which extracts features of mentions and entities from their contexts automatically. Specifically, given the context of a mention and one of its candidate entities' context, we introduce the co‐attention mechanism to learn the relatedness between the mention context and the candidate entity context, and build the mention representation in consideration of such relatedness. Moreover, we propose a context‐aware graph convolutional network for entity representation, which takes both the graph structure of the candidate entity and its relatedness with the mention context into consideration. Experimental results show that our model consistently outperforms the baseline methods on five widely used datasets.     

SESF-Fuse: an unsupervised deep model for multi-focus image fusion

Neural Computing and Applications - Muti-focus image fusion is the extraction of focused regions from different images to create one all-in-focus fused image. The key point is that only objects...     

一种提升泵车臂架位置检测精度的工程应用解决方案

针对在利用倾角传感器实现混凝土泵车之类的大型操作机的臂架姿态的间接测量方案中存在的因为臂架的柔性和操作机在不同姿态下自身水平状态的不同可能导致的臂架末端的理论计算值存在较大测量误差的问题,采用了一种在臂架的不同位置增加传感器来实现对臂架柔性变形大小和自身水平状态的实时检测的方法,并着重研究了针对具体的柔性变形及水平状态变化所导致的理论偏差进行实时补偿的切实可行的方法,实验检测的数据证明,相对补偿前臂架的定位精度提升了75％以上.     

Hybrid predictive dynamics: a new approach to simulate human motion

A new methodology, called hybrid predictive dynamics (HPD), is introduced in this work to simulate human motion. HPD is defined as an optimization-based motion prediction approach in which the joint angle control points are unknowns in the equations of motion. Some of these control points are bounded by the experimental data. The joint torque and ground reaction forces are calculated by an inverse algorithm in the optimization procedure. Therefore, the proposed method is able to incorporate motion capture data into the formulation to predict natural and subject-specific human motions. Hybrid predictive dynamics includes three procedures, and each is a sub-optimization problem. First, the motion capture data are transferred from Cartesian space into joint space by using optimization-based inverse kinematics (IK) methodology. Secondly, joint profiles obtained from IK are interpolated by B-spline control points by using an error-minimization algorithm. Third, boundaries are built on the control points to represent specific joint profiles from experiments, and these boundaries are used to guide the predicted human motion. To predict more accurate motion, the boundaries can also be built on the kinetic variables if the experimental data are available. The efficiency of the method is demonstrated by simulating a box-lifting motion. The proposed method takes advantage of both prediction and tracking capabilities simultaneously, so that HPD has more applications in human motion prediction, especially towards clinical applications.     

Predictive simulation of human walking transitions using an optimization formulation

A general optimization formulation for transition walking prediction using 3D skeletal model is presented. The formulation is based on a previously presented one-step walking formulation (Xiang et al., Int J Numer Methods Eng 79:667–695, 2009b). Two basic transitions are studied: walk-to-stand and slow-to-fast walk. The slow-to-fast transition is used to connect slow walk to fast walk by using a step-to-step transition formulation. In addition, the speed effects on the walk-to-stand motion are investigated. The joint torques and ground reaction forces (GRF) are recovered and analyzed from the simulation. For slow-to-fast walk transition, the predicted ground reaction forces in step transition is even larger than that of the fast walk. The model shows good correlation with the experimental data for the lower extremities except for the standing ankle profile. The optimal solution of transition simulation is obtained in a few minutes by using predictive dynamics method.     

聚合物泥浆抑制剂的发展动向

聚合物抑制剂是聚合物泥浆的重要组成部分。本文报导了聚合物抑制剂的发展动向,介绍了作为聚合物泥浆抑制剂的阳离子型聚合物、复合离子型聚合物、非离子型聚合物及改性的部分水解聚丙烯酰胺。     

基于互联网实现多种信息传输技术

随着信息技术的迅速发展,使用互联网实现楼宇内电话、电视、电脑、安防和环境监控、计量数据等信息的合路传输,是实现智能家居和数字楼宇的一种主要发展趋势。最终目的,实现对物和过程的智能化感知。文章首先介绍信息合路编码、中央控管电路,然后介绍网络接口电路原理和系统体系构架。重点介绍多种多样的信息传输技术。它对现代楼宇信息化、智能化建设有很好的参考作用。