运动图像处理在汽车车型识别中的应用

本文介绍了“多品种混流机器人喷漆自动线的汽车车型识别系统”的一种算法,提出了基于运动序列图像的自适应阈值判别法和利用特征匹配法解决了同种车型的图像在结构上产生局部变化的识别问题。     

LCD定标器X级图像缩放引擎的VLSI设计

LCD定标器的X级图像缩放引擎负责对输入图像进行水平方向的缩放．文中介绍了定标器的总体结构，以及实现X级图像缩放引擎的算法及其滤波器结构，并详细地阐述了X级图像缩放引擎硬件实现中的时序关系．     

一种邮政编码自动识别系统

利用数字图像处理技术对目标对象的自动识别原理，通过模糊识别邮政编码，实现信件分拣自动化，实验结果表明，该系统分拣效率达5件／s以上，误拣率约5％，可提高邮政信件分拣效率，加快邮件传递速度。     

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。     

基于计算机扫描技术的沥青混合料集料质量均匀性评价

运用 CT（Computer Technology）获得沥青混合料的内部微观结构已成为现阶段研究热点之一,但是现阶段结合沥青混合料的 CT扫描断面图具有的特点进行数字图像系统处理的研究相对较少,而且将其用于区分内部材质的技术目前比较粗糙,无法有效将数字图像处理和混合料无损检测技术结合起来。基于混合高斯模型（GMM）E M算法的基础上,对沥青混合料的集料特性进行分割,进而对细观结构的质量均匀性分析进行判断,最后通过试验深层次探索内部体积组成结构情况。研究结果表明本文采用的混合高斯模型能较好的对 CT扫描断层图片进行处理,通过扇形扫描方法可对沥青混合料集料的分布情况进行判断,进而通过对集料颗粒的面积比进行统计分析,进而评价沥青混合料的集料分布均匀性,本文研究结果可为沥青混合料微观领域研究提供借鉴和参考意义。     

Research on the high-speed railway catenary systems online real-time testingEI北大核心

Research purposes: Some catenary system vibrated largely after the train since Chinese high-speed railway running, which came from an oral report of one rail worker on duty. Its accurate displacement must be measured in order to solve the problem. The measurement technique based on image has the advantages of non-contact and dynamic which is suitable for unique structure such as catenary system. The computer gets displacement value through analyzing image which may ensure train's safety when on-line test is carrying out. The research not only can be used to analyze the cause of abnormal existing catenary shaking and swaying amplitude, but also can provide the technical support for catenary of electrified railway online real-time test. Research conclusions: (1) The measured amplitude of cantilever, shoulder brace of positive feeder and carrier cable was small relatively and consistent with other normal sections of the whole line. (2) The interaction between catenary and pantograph was the main reason for its vibration, without the coupling effect between up-bound and down-bound. (3) The accurate value of test result indicated that the amplitude of catenary is under the range allowably, which verified the uncertainty of human sense and further clarified the safety hazard. (4) The non-contact measurement technique based on image can get the dynamic real time test data and have simple and convenient operation, which supplies subtle and suitable way for high-speed railway catenary systems real-time on-line test.     

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。     

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.