隧道三维激光扫描测算一体化技术方案与实践北大核心CSCD

三维激光扫描技术已在隧道工程中得到广泛应用,但其内外业脱节、人工操作过多、实时性不足等问题日益凸显。文章结合工程实践,提出三维激光隧道扫描测算一体化技术方案,通过隧道设计模型录入、坐标里程解算、点云自动过滤、点云降采样与地物分离等,对点云进行特征值提取,得到兼顾规模、精度、效率的点云数据模型;通过点云与设计、点云与点云的对比解算,得到隧道工程质量安全相关成果。该技术方案在某铁路隧道工程中进行实践,可将内外业工作总时间缩短至20 min以内,自动化程度高,成果精度好,具有很好的推广价值。     

用于目标检测和精确定位的水下机器人视觉系统

基于目标检测和精确定位的ＡＵＶ（Ａｕｔｏｎｏｍｏｕｓ Ｕｎｄｅｒｗａｔｅｒ Ｖｅｈｉｃｌｅ）视觉系统是水下智能机器人感知水下环境信息、进行自主作业的关键技术。本文着重介绍了视觉系统的工作原理、模块结构、特征提取和目标检测与定位算法。最后给出了仿真试验结果,以说明系统工作的有效性和实用性。     

基于最大方差理论的大津法在沥青混合料数字图像分割中的应用

针对目前沥青混合料自动检测的要求,借助于数字图像处理技术,给出最大方差理论在沥青混合料智能检测与参数提取中的应用,可为实现沥青混合料自动检测与分析奠定良好的基础。     

Image segmentation based on competitive learning

lmage segment is a primat.‘y step in image analysis of unexploded ordnance (UXO) detection by ground penetrating radar (GPR) sensor which is accompanied with a lot of noises and other elements that affect the recognition of real target size. In this paper we bring forward a new theory, that is, we look the weight sets as target vector sets which is the new cues in semi-automatic segmentation to form the final image segmentation. The experiment results show that the measure size of target with our method is much smaller than the size with other methods and close to the real size of target.     

基于高通滤波和直方图均衡的钢轨裂纹红外图像增强技术

针对钢轨裂纹红外图像采集过程中产生的噪声大、对比度低的问题,以及传统直方图均衡化方法在对红外图像增强时灰度级减少和细节信息丢失等不足,提出频域增强与空域增强相结合的红外图像增强算法,以弥补传统算法在红外图像增强时的不足。在空间域上采用直方图均衡化对红外图像进行处理,提高图像对比度降低图像噪声;在频率域上采用高通滤波对红外图像进行锐化处理,增强图像的边缘和细节信息。仿真结果表明:该算法在对钢轨裂纹红外图像增强时很好地抑制了背景噪声,而且有效地凸显了钢轨裂纹内部微弱的细节纹理,保护图像的细节信息,为更好地提取钢轨裂纹的缺陷信息提供条件。     

基于图像变化检测的舰船毁伤信息提取问题研究

信息化条件下,舰船毁伤效果评估对舰船毁伤信息的提取提出了更高的要求。文章对基于图像变化检测的舰船毁伤信息提取问题进行了研究,首先对舰船毁伤前后的图像进行配对,然后利用变化检测法对图像变化的纹理特征和几何特征进行检测,提取舰船毁伤评估所需要的毁伤信息。     

基于粒子滤波的无人机侦察图像跟踪算法研究

针对无人机侦察图像跟踪的实时性以及战场环境复杂的特点,研究了在复杂背景下实现对单一目标跟踪,提出了一种基于粒子滤波的快速目标跟踪算法,通过计算机仿真将此方法与传统的目标跟踪方法进行了对比,实验结果表明,该算法能够稳健地跟踪目标,具有很好的准确性、实时性和鲁棒性。     

基于MATLAB与LabVIEW的回波信号处理与分析

针对MATLAB与LabVIEW软件的不同特性,提出利用编程实现和虚拟实验相结合的方式对某声纳接收到的回波信号进行处理。信号的处理与分析是MATLAB与LabVIEW的强项,用户可以很轻松地构建各种复杂的信号处理与分析系统,操作简便,并且形象直观,大大提高了信号处理与分析的能力、精度和效率。     

Hierarchical Non-linear Image Registration Integrating Deformable Segmentation

IntroductionSegmentation and registration are two impor-tant problems in the field of medical image analy-sis. Traditionally, solutions have been developedfor each of these two problems in relative isolationfrom the other, but with increasing dependence onthe existence of a solution for the other. For exam-ple, model-based segmentation methods[1,2]need toregister individual data sets to a common frame ofreference, so that statistics about the models canbe gathered to guide the evolution of the…     

A New Range Sidelobe Suppression Technique for Randomly Intermittent Spectra HF Radar Signal

The randomly intermittent spectra (RIS) signal is employed to combat spectrum congestion in radar and other radio services to evade the external interferences in high-frequency (HF) and ultrahigh-frequency (UHF)bands. However, the spectra discontinuity of the signal gets rise to high range sidelobes when matching the reflected echo, which is much more difficult for targets detection. So it is indispensable to investigate the technique for sidelobes suppression of the range profile when RIS signal is utilized, This paper introduced a new processing technique based on time domain filtering to lower the range sidelobes. A robust and effetive algorithm is adopted to solve the coefficients of the filter, and the restriction on the desired response of the filter is derived. The simulation results show that the peak range sidelobe can be reduced to -27dB from -9.5dB while the frequency band span (FBS) is 200kHz.