荧光磁粉探伤裂纹智能识别图像处理研究

磁粉探伤的发展趋势是自动化、智能化,而工件表面状况、真伪裂纹、工况条件等使得现有的检测识别方法难以满足工件表面裂纹缺陷自动检测识别的需要。在分析工件表面荧光磁粉图像特征及裂纹缺陷特征的基础上,研究表征裂纹邻域像素空间相关度的二维直方图分布,提出基于多重分块极值的图像边缘检测算法。根据裂纹邻域像素空间相关度参数,以及裂纹缺陷的长宽比、圆形度等特征,设计了基于Fisher线性判别方法的工件裂纹识别算法。以此为基础的荧光磁粉探伤工件裂纹缺陷自动检测识别技术,应用于列车轮轴检测线实时检测,裂纹缺陷的有效检出率达99%。     

基于烧结机尾断面图像处理系统的开发

介绍了DSP6711的硬件特性和烧结机尾断面图像检测、识别的原理及算法的选型,并运用基于DCT变换域的LDA特征的提取方法,实现了烧结机尾断面图像的自动识别.系统的实际运行是稳定和有效的.     

基于动态分频段FRA法的自耦变压器绕组轴向移位故障诊断

针对传统的频率响应分析(FRA)法无法识别自耦变压器绕组常见轴向移位故障的问题,提出基于动态分频段的FRA法:首先,搭建自耦变压器轴向移位故障模拟平台,获取不同轴向移位故障下绕组频响数据;其次,将幅频特性曲线波峰点与相频特性曲线C-L过零点频率相同的点作为预备分频点,同时将频响数据动态划分为多个频段,并绘制分频段极坐标图;然后,提取极坐标图的4个灰度梯度共生矩阵纹理特征和对应的归一化特征参数;最后,通过图形与特征的变化规律分析自耦变压器绕组的状态。试验验证结果表明:采用基于动态分频段的FRA法,生成的极坐标图数据点重叠情况得到改善,有利于图形分析和特征提取;不同绕组发生轴向移位故障时,各频段极坐标图变化趋势明显;同一绕组发生不同程度轴向故障时,极坐标图随故障程度增加差异呈变大的趋势;采用基于动态分频段的FRA法能准确区分自耦变压器轴向移位的故障绕组与故障程度,并能为自耦变压器现场故障诊断提供参考。     

一种基于数字图像处理技术的沥青混合料均匀性评价方法

提出一种基于数字图像处理技术的沥青混合料芯样水平切片均匀性评价方法及相应的评价指标,该方法利用数字图像处理技术对沥青混合料芯样水平切片进行处理,通过分析芯样图片中集料颗粒的转动惯量可以定量的评价沥青混合料离析情况。     

无证驾驶自动查处系统的设计与探讨

文章结合现有的无证驾驶查处方式带来的问题和弊病,基于智能交通系统的相关技术,介绍了无证驾驶自动查处系统功能模块的设计、安装及关键技术,为无证驾驶系统的研发提供参考。     

Virtual 3D city model as a priori information source for vehicle localization system

This paper aims at demonstrating the usefulness of integrating virtual 3D models in vehicle localization systems. Usually, vehicle localization algorithms are based on multi-sensor data fusion. Global Navigation Satellite Systems GNSS, as Global Positioning System GPS, are used to provide measurements of the geographic location. Nevertheless, GNSS solutions suffer from signal attenuation and masking, multipath phenomena and lack of visibility, especially in urban areas. That leads to degradation or even a total loss of the positioning information and then unsatisfactory performances. Dead-reckoning and inertial sensors are then often added to back up GPS in case of inaccurate or unavailable measurements or if high frequency location estimation is required. However, the dead-reckoning localization may drift in the long term due to error accumulation. To back up GPS and compensate the drift of the dead reckoning sensors based localization, two approaches integrating a virtual 3D model are proposed in registered with respect to the scene perceived by an on-board sensor. From the real/virtual scenes matching, the transformation (rotation and translation) between the real sensor and the virtual sensor (whose position and orientation are known) can be computed. These two approaches lead to determine the pose of the real sensor embedded on the vehicle. In the first approach, the considered perception sensor is a camera and in the second approach, it is a laser scanner. The first approach is based on image matching between the virtual image extracted from the 3D city model and the real image acquired by the camera. The two major parts are: 1. Detection and matching of feature points in real and virtual images (three features points are compared: Harris corner detector, SIFT and SURF). 2. Pose computation using POSIT algorithm. The second approach is based on the on–board horizontal laser scanner that provides a set of distances between it and the environment. This set of distances is matched with depth information (virtual laser scan data), provided by the virtual 3D city model. The pose estimation provided by these two approaches can be integrated in data fusion formalism. In this paper the result of the first approach is integrated in IMM UKF data fusion formalism. Experimental results obtained using real data illustrate the feasibility and the performances of the proposed approaches.     

基于文化粒子群网络优化算法的医学图像研究

文章提出了基于文化粒子群的网络优化算法的医学图像方法，通过在50例唇裂矫正术中运用BP神经网络进行学习．对唇部进行解剖观察和美学分析，在矫正修复手术中不断学习和调整来接近期望输出，并通过实验仿真及客观的图像提出了评估准则。实验结果表明，在美学研究基础上的基于文化粒子群BP神经网络的医学图像研究，适用于唇裂的矫正修复。     

Development of an LIF image processing technique for measuring drop sizes in a pre-swirl spray

Depth of field effects in laser sheet imaging were considered for droplet sizing of a pre-swirl spray. A pre-swirl spray is formed before the hollow-cone type main-swirl spray from a D.I. gasoline injector, and shows transient characteristics with high axial velocity. A microscopic imaging technique was applied to obtain high spatial resolution LIF tomograms of the pre-swirl spray. A 1 mm thick Nd:YAG laser sheet was used as a light source to make the LIF tomograms that were imaged using a high-resolution CCD camera. The droplet sizing of the pre-swirl spray was carried out using an image processing technique. In the image processing procedure, the laser sheet-straddling large-sized droplets were carefully taken into account to remove the errors caused by the depth of field effects from the limited thickness and the energy distribution of the laser sheet. The mean intensity of the individual droplets and the line profile of the LIF signal around the droplet edge were inspected to screen the laser sheet-straddling large-sized droplets. In order to consider the effects of the size-dependent LIF signal intensity, the size-classified or ensemble-averaged mean intensity of the individual droplets was introduced. The mean droplet sizes such as AMD and SMD were calculated using only screened droplets, and they slightly increase before considering the depth of field effects.     

图像分割在工件图像视觉检测中的应用

在介绍图像分割的主要特征的基础上,分析了目前几种典型图像分割方法。针对工件图像视觉检测中图像分割特点,提出了将边缘检测和域值分割方法相结合来分割工件图像的一种新方法,并开发了相应的软件。实验验证该方法用于工件图像测量,能很好消除图像噪声,得到连续的图像边界,并且定位较准,可以有效地提高检测系统的精度。     

海量数据的均匀稀化

为了给后续曲面重构提供合适、均匀分布的数字化型面,从激光测量数据的特点出发,即测点本身趋于均匀分布的情况下,根据古典概率提出了平面数据均匀稀化的4种方案;然后,在曲面局部趋于平面的假设下,又将平面稀化方案扩展到三维空间.由于稀化过程中不需要考虑曲面的具体特征,给实际操作带来了极大的方便.对3个实测数据点的稀化测试,也进一步验证了本文提出的算法是行之有效的.