Adaptive visual target detection and tracking using weakly supervised incremental appearance learning and RGM-PHD tracker

Multiple visual target tracking is a challenging problem due to various uncertainties including occlusion, miss-detection and noisy measurement. Most tracking approaches utilize an object-specific detector, pre-trained on many labeled images, to provide suitable measurements for their tracking system. In this paper, we use a simple background subtraction detector which only needs the background image to localize targets independent of their shape or type. In order to cope with the uncertainties resulted by the detector, we propose an adaptive appearance model and develop an incremental appearance learning algorithm to learn the target appearances in time. The proposed method employs the background information and our defined keypoints’ miss-matched history to adapt the target appearances within different frames. Furthermore, we combine Refined Gaussian Mixture Probability Hypothesis Density (RGM-PHD) tracker with the detectors to keep target trajectories and handle uncertainties. The experiments conducted on several video datasets show the effectiveness of our proposed method.     

汽车大梁用热轧H型钢的现状及标准综述

简要介绍了汽车大梁所使用的H型钢的现状，分析了汽车大梁用热轧H型钢标准研究的主要技术内容。     

New trends on moving object detection in video images captured by a moving camera: A survey

This paper presents a survey on the latest methods of moving object detection in video sequences captured by a moving camera. Although many researches and excellent works have reviewed the methods of object detection and background subtraction for a fixed camera, there is no survey which presents a complete review of the existing different methods in the case of moving camera. Most methods in this field can be classified into four categories; modeling based background subtraction, trajectory classification, low rank and sparse matrix decomposition, and object tracking. We discuss in details each category and present the main methods which proposed improvements in the general concept of the techniques. We also present challenges and main concerns in this field as well as performance metrics and some benchmark databases available to evaluate the performance of different moving object detection algorithms.     

Effect of geometrical factors on stability characteristics of portal frames

This paper is concerned with the effect of slanting the columns and changing the ratio of the member lengths on the buckling and post-buckling behaviour of portal frames. Two types of structures are considered: hinged- and rigid-base frames, each type subjected to two loading patterns. In the first pattern (perfect loading), equal vertical loads are applied to the nodes. The second pattern (imperfect loading) consists of the same vertical loads and, additionally, of a horizontal nodal force. Numerical results are presented that show the beneficial effect of slanting the columns by negative angles (i.e. clockwise for the left-hand column and anticlockwise for the right-hand one), and the degrading effect of slanting the columns by positive angles. The effect has been observed both in perfect frames and in the frames subjected to imperfect loading. The paper considers also the effect of the frame geometry on the structure's sensitivity to imperfections. The imperfection sensitivity analysis of the frames is carried out according to a definition of sensitivity which differs somewhat from that commonly used.     

基于ARM和DSP空中运动目标实时跟踪系统研究

对空中目标物体实时跟踪目前主要采用雷达探测的方法,但时常会受到电磁场与电磁波的干扰,降低了探测的准确性,为解决此类问题,提出了一种基于空中视觉实时跟踪系统的解决方案.该方案适用于小范围空中动态物体的跟踪,包括动态目标的差值提取,二值图像的滤波和模板图像的实时更新,以及动态目标的特征提取、云台控制.为提高系统的准确检测性,提出了一种基于改进的动态模板匹配与帧间差分相结合的空中目标检测方法.该方法有效地解决了电磁场干扰、环境变化使动态目标无法捕捉的问题,根据实验表明,该系统能够很好地检测到空中动态物体,具有很好的鲁棒性、实时性和清晰度.     

基于对数域同态滤波的时延估计算法研究

针对水声信道中窄带信号的多途时延估计问题,本文在对复倒谱时延估计方法进行研究的基础上,提出了一种基于对数域同态滤波的时延估计算法.结合复倒谱与同态滤波思想,将接收的窄带信号首先变换到对数域,然后与本地存储的信号进行谱减法,再对相减后的信号进行滤波以消除残余的信号与噪声成分,最后将其恢复到时域以获取多途时延估计.与传统的匹配滤波/相关处理以及复倒谱分析方法相比,本文算法具有时延估计精度高、噪声抑制能力较强等特点.仿真与湖试数据处理结果证明了该方法的有效性.     

一种优化的多视点视频编码预测结构

首先分析了JMVC的参考预测结构,利用1个Go P(Group of Picture)中不同时间层上的帧与其参考帧之间的相关度不同和不同时间层上的帧数目也不同的特点,提出了去除奇数视点最高和次高时间层的视点间预测,并增加偶数视点非关键帧的最低和次低时间层的视点间预测的预测结构。实验结果表明,提出的预测结构基本不影响视频质量,且表现出了更加出色的编码效率,编码的复杂度减少幅度高达15%,输出码率也有所减少,较好地改善了编码的实时性能。     

球型毫米波金属桁架天线罩研究

从球形毫米波天线罩的空间分块设计、金属桁架和连接节点设计、透波窗口设计以及安装架设方式等方面进行了详细论述,并通过一直径7 m、工作在20 GHz的金属空间桁架天线罩的设计实例和实验研究,证明文中所用方法行之有效,可推广应用于各种大型天线罩的电性能分析和选形设计。     

西宁曹家堡机场T2航站楼钢结构安装技术

西宁曹家堡机场T2航站楼钢结构工程具有气候环境恶劣、现场条件极为有限、桁架结构复杂、倾斜钢柱安装难度大、结构稳定性差等特点.根据工程总体施工计划和工程特点,屋盖钢结构采用分段拼装、原位安装的施工方案.重点介绍了起重机械配置方案、支撑格构架设计方案、钢柱和桁架的吊装方案、测量控制方案.实践证明,所采取方案保证了桁架安装满足要求.     

High resolution melting curve analysis with MATLAB-based program

High resolution melting curve analysis (HRM) is an emerging new method for interrogating and characterizing DNA samples. It has been used as a powerful tool for gene mutation and single-nucleotide polymorphism (SNP) detection with high throughput and low cost. Commercially available HRM analysis systems are mostly proprietary and expensive. It lacks the flexibility for the end users and researchers to incorporate new analysis algorithms into the existing system. This paper presents the development of a MATLAB-based open software program for high resolution melting curve analysis. Key analysis functions, such as to obtain the first derivative curve using Savitzky–Golay filter, to identify the melt region, subtraction of background fluorescence and curve normalization, are introduced, followed by case studies of HRM analysis using the developed software program.