基于双目视觉的原木材积自动检测系统

根据原木材积检测的特点,针对传统人工检尺存在的主要问题,基于双目视觉理论,设计了一种由CCD摄像机、单片机和上位机图像处理软件组成的自动化测量系统.选用HYC-600摄像机组建双目视觉前端,并给出了单片机信号采集处理板、光电编码器和光电开关等关键技术的设计方法,完成了双目标定、Bouquet校正、三维重构和各功能模块的软件开发.实验结果表明：该检测系统能有效克服人工检尺的缺点,成本低、精度高、可靠性强、安装使用方便.     

基于图像识别与移动通信的木材运输稽查系统

基于智能终端技术,设计了原木图像检尺算法,开发出手机端的原木检尺子系统,以获取木材运输原始发车原木图像和检尺码单数据并实时上传。通过基于移动通信的运输执法子系统,执法人员异地下载原始发车原木图像,与实际运输情况比对,以实现自动精确检查。在发现违法运输后,应用智能手机现场取证,打印处罚单。原木图像与GPS信息保证了执法取证的严密性与客观性。实验表明,我国南方林区的木材运输检查站在本系统支持下,能够实现运输检查智能化与规范化,自动放行合法车辆,缩短稽查时间,有效地提高木材运输效率,促进林业交通环境的和谐发展。     

基于计算机视觉的自动矫正数控系统

基于机器视觉技术,利用OpenCV计算机视觉开源库作为开发函数库,以工业相机和三轴雕刻机作为实验平台,为数控系统进行视觉矫正系统开发.首先对装夹后PCB板采集Mark点,直线检测完成后,利用角点检测对Mark点进行定位.通过霍夫变换得到世界坐标系下的直线方程,以此求取当前待加工PCB板的装夹位置和姿态.最后通过图像坐标和机械坐标的变换关系对加工位置信息进行纠偏处理.针对数控系统PCB板加工中出现的装夹误差问题,设计并开发了基于机器视觉技术的数控系统视觉矫正系统.通过实验和具体误差数据证明了本系统达到了PCB板的加工精度要求.     

机器视觉技术在交通领域的应用探讨

随着计算机的普及和相关软件的不断更新升级,机器视觉技术在交通领域所发挥的作用愈为重要。其应用范围较广,主要包括交通指挥、视频检测系统、车牌识别和智能车辆的安全保障系统等。就利用机器视觉技术进行优化交通管理上的进展进行了探讨,以供我国同类研究人员参考。     

基于小区域跟踪的多晶硅视频检测系统

为实时测量多晶硅棒直径,研制了多晶硅棒径在线视频检测系统.该系统采用双相机成像的机器视觉方法实现目标硅棒的监测,采用左中右差分的图像分割技术提取目标,采用基于小区域的质心跟踪算法跟踪目标.系统标定后,可实时测量还原炉内多晶硅棒的直径.实验结果表明:该系统能检测微弱边缘,在直径为8~150 mm的范围内,测量精度高于工业视觉图像测量的要求.     

机器视觉新技术在自动表面检测中的探讨

介绍了机器视觉的作用、应用领域与国内外研究现状,提出了机器视觉新技术的研究及其在自动表面检测中的应用.     

基于机器视觉的公路交通标志自动化巡检系统

针对既有交通标志巡检的调查手段和分析方法存在的成本高、效率低、精度低的弊端,提出了一种基于机器视觉的公路交通标志自动化巡检系统,实现对公路交通标志的移动式实时检测与分析。首先利用YOLO （You Only Look Once） 算法,将机器视觉技术运用到交通标志的检测中,加快了检测速度。然后给出了交通标志自动化巡检系统的系统构架、系统结构与功能及数据管理方案。最后利用该系统进行实测。实测结果显示,该自动化巡检系统能够准确地检测交通标志、道路标线及路面坑塘,具有较高的测试精度及较好的测试效果。     

基于机器视觉的螺母垫圈分拣系统设计

介绍了基于机器视觉的螺母垫圈自动分拣系统的工作原理、系统组成及检测算法.该系统能够对生产线上螺母垫圈的内外圆直径、同轴度等进行实时动态检测.并触发分拣子系统对螺母垫圈废品予以剔除,实现了产品关键尺寸快速检测和等级分类.     

频闪动态干涉法测量离面位移的研究

频闪视觉测量和频闪干涉测量代表了目前先进的微机电系统动态测试技术,尤其在非接触无损测量技术有重要意义.通过微机电三维静动态测试系统,综合运用等厚干涉原理和基片曲率法,实时测量,计算出镀膜样品在升温和退火过程中应力的变化.结果表明,该方法适合测量微机电器件的离面位移.     

基于机器视觉的桥梁检测技术现状及发展

基于机器视觉的桥梁检测技术相对传统检测技术具有自动化程度高、检测效率好、检测成本低、不影响交通以及高耸构件检测便捷等优点。文中分析了采用机器视觉进行桥梁检测的研究应用现状;梳理了进行图像采集、病害自动识别以及裂缝测量的技术手段与方法,并分析了每种手段与方法的优缺点与适用范围。最后提出了该技术的发展方向:重点发展高效的图像获取手段与细微裂缝的自动识别算法。     

基于两点三次样条插值算法的大尺寸LCD图像缩放引擎设计

本文针对LCD控制器的图像缩放引擎,提出了一种基于两点的三次样条插值算法。该算法实现简单,不仅节省硬件开销,而且可以取得比nearest、bilinear插值算法更好的图像处理效果。文中详细阐述了图像缩放引擎的硬件实现结构以及插值滤波器的实现原理。并利用Q值评价法对提出的算法进行了客观评价,评价结果表明该算法可以取得接近于bicubic的图像处理效果。最后对图像缩放引擎进行了FPGA验证,验证结果表明图像缩放引擎工作正确,图像显示效果良好。     

Focusing azimuth-invariant bistatic synthetic aperture radar data based on a polynomial model

In this paper, a focusing approach is presented to widen the use of efficient monostatic imaging algorithms for azimuth-invariant bistatic synthetic aperture radar (SAR) data. The bistatic range history is modeled by a polynomial of azimuth time. Using this model, an analytic form of the signal spectrum in the 2D frequency domain is derived, and a simple single-valued relation between the transmitter and receive ranges is established. In this way, a lot of monostatic image formation algorithms can be extended for the bistatic SAR data, and a bistatic chirp scaling algorithm is developed as an application of the new approach. This algorithm can be used to process the azimuth-invariant bistatic configuration where the transmitter and receiver platforms are moving on parallel tracks with the same velocity. In addition, some simulation results are given to demonstrate the validity of the proposed approach.     

Automatic identification of cracks from borehole image under complicated geological conditions

Identifying cracks from the spread image of a borehole wall is one of the most common usages of borehole imaging method. The manual identification of cracks is time-consuming and can be easily influenced by objective judgment. In this study, firstly, the image translation from RGB color model to HSV color model is done to highlight the structural plane region, which is closer to the color recognition of human sight; secondly, the Saturation component is filtered for further processing and a twice segmentation method is proposed to improve the accuracy of automatic identification. The primary segmentation is based on the statistics of saturation over a longer borehole section and can give a rough estimation of a crack. Then, the pixels are shifted in the reverse direction to the sine curve estimated and make the centerline of the crack flat. Based on the shifted image, the secondary segmentation is done with a small rectangle region that takes the baseline of the roughly estimated crack as its centerline. The result of the secondary segmentation can give a correction to the first estimation. Through verifying this method with actual borehole image data, the result has shown that this method can identify cracks automatically under very complicated geological conditions.     

Image series segmentation and improved MC algorithm

A semiautomatic segmentation method based on active contour is proposed for computed tomography （CT） image series. First, to get initial contour, one image slice was segmented exactly by C-V method based on Mumford-Shah model. Next, the computer will segment the nearby slice automatically using the snake model one by one. During segmenting of image slices, former slice boundary, as next slice initial contour, may cross over next slice real boundary and never return to right position. To avoid contour skipping over, the distance variance between two slices is evaluated by an threshold, which decides whether to initiate again. Moreover, a new improved marching cubes （MC） algorithm based on 2D images series segmentation boundary is given for 3D image reconstruction. Compared with the standard method, the proposed algorithm reduces detecting time and needs less storing memory. The effectiveness and capabilities of the algorithm were illustrated by ,experimental results.     

洪量随历时变化的标度性质研究

以长江流域3个水文站的洪水资料为例，应用标度理论，对洪量随历时变化的标度特性进行了研究。研究结果表明：在一定的历时范围内，年最大洪量随历时变化具有单标度性质。由洪量随历时变化的单标度性质，建立了洪水强度历时公式，可直接求出不同历时的年最大洪量值，与常规方法计算结果相比，二者十分接近。     

Active Contours and Mumford-Shah Segmentation Based on Level Sets

IntroductionThe basic idea in active contour models orsnakes is to evolve a curve,subject to constraintsfrom a given image,in order to detect objects inthat image.For instance,starting with a curvearound the object to be detected,the curve movestoward its interior normal and has to stop on theboundary of the object.LetΩ be a bounded open subset of R2 ,with Ω its boundary. Let u0 ∶Ω→ R be a given image,and C( s)∶ [0 ,1 ]→ R2 be a parameterized curve. Inthe classical snakes and active…     

面向智能交通的单目视觉测距方法研究

与前方车辆距离是影响行车安全的重要因素,因此本文提出一种面向未来智能交通的前方车辆单目视觉测距方法.首先,提出融合物联网、智能识别、云计算技术的车联网模型,车辆可实时向车联网回传位置信息及前车图像,请求附近交通标志及前方车辆几何尺度信息,车辆端可计算图像坐标系下车道标志线、交通标志、车辆尺度信息.然后,建立单目相机数学模型,介绍以交通标志、车道分界线为合作标志的单目视觉测距方法.最后,综合应用单目视觉测距方法,设计了前方车辆自适应视觉测距方案.通过仿真实验,证明了单目视觉测距方法的正确性与有效性,可丰富驾驶辅助系统的前方车辆测距手段.     

An improved scalar Costa scheme based on Watson perceptual model

An improved scalar Costa scheme （SCS） was proposed by using improved Watson perceptual model to adaptively decide quantization step size and scaling factor. The improved scheme equals to embed hiding data based on an actual image. In order to withstand amplitude scaling attack, the Watson perceptual model was redefined, and the improved scheme using the new definition can insure quantization step size in decoder that is proportional to amplitude scaling attack factor. The performance of the improved scheme outperforms that of SCS with fixed quantization step size. The improved scheme combines information theory and visual model.     

Visual multi-secret sharing with friendliness

Visual secret sharing （VSS） was used in the literature to encode and decode secret images until visual multi-secret sharing （VMSS） was proposed. Distinctly, multiple secret images can be encoded or decoded at a time in VMSS; however, only one secret image can be done in VSS. In VMSS, secrets are encoded into noise-like shares which have finally been stacked altogether so as to disclose each of the secrets by specific operations, such as rotating, flipping and sliding. Though the noise-like shares can be decoded by those operations, it is just like a fly in the ointment since they are hard to manage, to recognize and even to stack orderly. Based on some researches about user-friendly VSS for generating meaningful shares, a new friendly VMSS scheme is presented in this paper for achieving two main goals. One is trying to encode multiple secrets at a time and the other is making the decoding process easy to manage. The experimental results prove that our proposed scheme does work.