Image edge detection based tool condition monitoring with morphological component analysis

The measurement and monitoring of tool condition are keys to the product precision in the automated manufacturing. To meet the need, this study proposes a novel tool wear monitoring approach based on the monitored image edge detection. Image edge detection has been a fundamental tool to obtain features of images. This approach extracts the tool edge with morphological component analysis. Through the decomposition of original tool wear image, the approach reduces the influence of texture and noise for edge measurement. Based on the target image sparse representation and edge detection, the approach could accurately extract the tool wear edge with continuous and complete contour, and is convenient in charactering tool conditions. Compared to the celebrated algorithms developed in the literature, this approach improves the integrity and connectivity of edges, and the results have shown that it achieves better geometry accuracy and lower error rate in the estimation of tool conditions.     

基于计算机视觉的轮对轮缘磨耗动态测量方法的研究

应用计算机视觉技术动态测量轮对轮缘磨耗的尺寸,研究了电荷耦合器件(CCD)隔行扫描造成的运动模糊的消除、图像平滑、图像二值化、中心线提取、标定等技术,发现中值滤波平滑处理图像的精度高,最大类间方差法分割图像效果好,变窗"跟踪虫"轮廓跟踪法提取光带的中心线完整。现场检测结果和人工测量进行比较,结果表明:测量系统可以快速准确地实现轮对轮缘磨耗动态测量,检测误差不超过0.3 mm,满足车辆段现场动态检测的要求。     

利用平行透视投影模型的位姿迭代估计

提出了一种利用平行透视投影模型的高效位姿迭代估计方法来提高单目视觉测量系统的精度和鲁棒性.通过引入齐次坐标表示,避免了现有算法对平行透视投影参考点选择的限制.首先,研究了平行透视投影模型下使用齐次坐标求解目标位姿的方法,阐述了它的几何意义.然后,通过迭代的方式将其应用于一般透视模型下目标位姿的高精度估计.仿真实验结果表明,本文方法提高了基于平行透视投影模型的位姿迭代估计的精度,速度和抗噪性能.实物测量结果表明,本文方法的平移测量精度优于0.1 mm,旋转测量精度优于0.1°,可以满足各种视觉检测系统的要求.另外,使用标志点和图像特征亚像素定位技术还可进一步提高该算法的精度.     

基于预分割轮廓的CT图像亚体素表面检测方法

针对基于CT(computed tomography)图像检测分析中的点云提取精度与完整性问题,提出一种基于预分割轮廓的高精度、高完整性的亚体素表面检测方法。首先采用Otsu分割算法提取CT图像的体素级轮廓点集,并以此作为粗定位轮廓自适应地生成用于亚体素表面检测的完备感兴趣区域(region of interest,ROI);然后提出一种基于梯度非极大值抑制的表面体素判定方法,避免了梯度阈值选择难题;最后基于3D Facet模型定位亚体素级表面点位置。实验结果表明,该方法能有效改善传统亚体素检测方法的轮廓丢失、伪边严重等问题,轮廓定位误差小于0.2个体素,同时能够取得3倍以上的计算加速比。     

基于彩色图像的高速目标单目位姿测量方法

针对风洞分离实验对于视觉测量系统的高精度、大视场、高速的测量要求,提出一种基于单目摄像机的风洞运动目标位姿测量方法。该方法利用单目摄像机进行运动目标位姿信息测量,相比于双目测量方法具有设备简单、视场大的优点。首先提出一种基于靶标特征点相互约束关系的参数优化方法,采用复合式靶标实现摄像机的快速高精度标定;针对目标运动图像处理,提出一种基于图像差叠法和标记点位置估计的图像快速分割与目标定位方法,实现图像特征的快速准确定位;针对单目测量要求及目标运动特性,提出一种基于方向估计标记点布局方式,实现合作标记点的快速识别和提取;最后利用单目视觉原理求解运动目标的位置和姿态信息,通过实验室模拟实验完成了测量系统的精度验证,在1 m×1 m视场范围内,其位移测量精度可达到0.19 mm,俯仰和偏航角测量精度可达到0.18°。     

船体零件几何尺寸测量图像分割方法研究

针对船体零件表面划痕、锈蚀以及下表面成像等因素导致的伪边缘及边缘不连续问题,提出了基于边缘与 k-means 聚类的船体零件图像分割方法.对于表面划痕及锈蚀形成的伪边缘,在矩形边缘检测区域内利用轮廓法线方向与边缘梯度方向信息予以剔除;零件下表面成像导致的伪边缘,选取 k-means聚类区分零件的上下表面边缘;边缘不连续问题,基于测地距离和断点方向准确连接断点,形成封闭轮廓.实验结果表明,使用该方法可获得平滑、封闭的分割效果,船体零件的几何尺寸测量误差低于 ０.５mm ,且测得量值标准偏差的平均值为 ０.２６２mm ,测量重复性较高,有效保障了船体零件几何尺寸的测量精度.     

结合位姿约束与轨迹寻优的人体姿态估计

基于混合部件模型的人体姿态估计方法忽视了人体结构的对称位姿约束关系,从而导致对称部件容易被重复检测、人体姿态估计准确率较低,为此,提出一种基于位姿约束与轨迹寻优的姿态估计新方法。首先估计人体单部件和对称部件在单帧图像中的多个合理位置,利用对称部件之间的位姿约束关系构建标识部件。然后根据单部件和标识部件各自的目标优化函数,通过动态规划算法反复迭代获得初始轨迹候选集,再结合轨迹的全局特征剔除检测得分较低的运动轨迹。最后引入树形合约模型,联系时空上下文信息,准确求解出视频序列光滑且兼容的最优轨迹。在N-best、Outdoor Pose和Scene数据集中的实验结果表明,对于存在背景复杂、运动模糊、部件遮挡等问题的视频序列中,该方法平均姿态估计准确率达87%以上,有效减少了对称部件的误判,提高了视频中人体姿态估计的准确率。     

Evaluation of three pose estimation algorithms for model-based roentgen stereophotogrammetric analysis

Model-based roentgen stereophotogrammetric analysis (RSA) uses a three-dimensional surface model of an implant in order to estimate accurately the pose of that implant from a stereo pair of roentgen images. The technique is based on minimization of the difference between the actually projected contour of an implant and the virtually projected contour of a model of that same implant. The advantage of model-based RSA over conventional marker-based RSA is that it is not necessary to attach markers to the implant. In this paper, three pose estimation algorithms for model-based RSA are evaluated. The algorithms were assessed on the basis of their sensitivities to noise in the actual contour, to the amount of drop-outs in the actual contour, to the number of points in the actual contour and to shrinkage or expansion of the actual contour. The algorithms that were studied are the iterative inverse perspective matching (IIPM) algorithm, an algorithm based on minimization of the difference (DIF) between the actual contour and the virtual contour, and an algorithm based on minimization of the non-overlapping area (NOA) between the actual and virtual contour. The results of the simulation and phantom experiments show that the NOA algorithm does not fulfil the high accuracy that is necessary for model-based RSA. The IIPM and DIF algorithms are robust to the different distortions, making model-based RSA a possible replacement for marker-based RSA.     

融合改进 YOLOv5 算法的图像全站仪全自动测量方法

针对图像全站仪在无棱镜合作工作模式下无法实现目标点全自动测量的问题,提出一种融合改进YOLOv5算法的图像全站仪全自动测量方法。应用融合卷积注意力机制模块的YOLOv5算法,实现了反射片靶标的广角镜头识别与检测;应用目标自动照准算法,实现了反射片靶标中心的长焦镜头精确照准,进而实现目标点位置坐标的全自动测量。借助自研的图像全站仪开展了反射片靶标的识别与检测实验和目标点全自动测量实验。实验结果表明,利用改进的YOLOv5算法对反射片靶标的识别与检测的准确率可达98.65%;目标点全自动测量方法具有与人工照准测量方法相当的测量精度且测量效率较后者提高了1.5倍。所提方法具有较高的测量精度和测量效率,可广泛应用于无人值守的全自动测量工作场合。     

Automated identification of neurons in 3D confocal datasets from zebrafish brainstem

Many kinds of neuroscience data are being acquired regarding the dynamic behaviour and phenotypic diversity of nerve cells. But as the size, complexity and numbers of 3D neuroanatomical datasets grow ever larger, the need for automated detection and analysis of individual neurons takes on greater importance. We describe here a method that detects and identifies neurons within confocal image stacks acquired from the zebrafish brainstem. The first step is to create a template that incorporates the location of all known neurons within a population – in this case the population of reticulospinal cells. Once created, the template is used in conjunction with a sequence of algorithms to determine the 3D location and identity of all fluorescent neurons in each confocal dataset. After an image registration step, neurons are segmented within the confocal image stack and subsequently localized to specific locations within the brainstem template – in many instances identifying neurons as specific, individual reticulospinal cells. This image-processing sequence is fully automated except for the initial selection of three registration points on a maximum projection image. In analysing confocal image stacks that ranged considerably in image quality, we found that this method correctly identified on average ∼80% of the neurons (if we assume that manual detection by experts constitutes 'ground truth'). Because this identification can be generated approximately 100 times faster than manual identification, it offers a considerable time savings for the investigation of zebrafish reticulospinal neurons. In addition to its cell identification function, this protocol might also be integrated with stereological techniques to enhance quantification of neurons in larger databases. Our focus has been on zebrafish brainstem systems, but the methods described should be applicable to diverse neural architectures including retina, hippocampus and cerebral cortex.     

不规则金属物料的抓取位姿实时检测方法研究

为解决机器人抓取不规则金属物料时存在的抓取位姿难以准确判断的问题,在图像处理算法的基础上,提出一种基于轮廓和形心特征的抓取位姿判断方法.该方法将金属物料分为两种类型,一种是形心落在轮廓范围以外,另一种是形心落在轮廓范围以内.对于第一种物料,采用直线求交法确定抓取位姿,对于另外一种提出射线求交法确定抓取位姿.两种方法均是...     

以机器视觉为基础的刀具磨耗侦测系统研究

刀具的几何轮廓与工件加工精度有着密不可分的关系,若刀具因磨耗产生形状误差,会影响产品精度或造成产品品质不良,故需对其进行精确监控,以确保产品品质与精度。本文提出以机器视觉为基础的非接触式刀具磨耗侦测系统,针对常用的车床刀具加以探讨,运用数位影像处理方法,以视觉辅助系统测量刀具磨耗,解决了传统人工检测的安全性不足,避免了因刀具磨耗产生的形状误差而影响产品的精度与品质。     

CT序列医学图像交互式分割系统的设计与实现

交互式分割对于医学图像中正常组织以及病变组织的提取与分析起着重要的作用。文中将基于小波模极大值的边缘检测方法与交互式轮廓逼近思想相结合,根据CT序列图像中相邻图像的相似性与连续性设计开发了医学图像的交互式分割系统,增强了医学图像分割的自动化程度并取得了较好的分割效果。     

Reality-augmented virtual fluoroscopy for computer-assisted diaphyseal long bone fracture osteosynthesis: a novel technique and feasibility study results

In this paper, a novel technique to create a reality-augmented virtual fluoroscopy for computer-assisted diaphyseal long bone fracture osteosynthesis and feasibility study results are presented. With this novel technique, repositioning of bone fragments during closed fracture reduction and osteosynthesis can lead to image updates in the virtual imaging planes of all acquired images without any radiation. The technique is achieved with a two-stage method. After acquiring a few (normally two) calibrated fluoroscopic images and before fracture reduction, the first stage, data preparation, interactively identifies and segments the bone fragments from the background in each image. After that, the second stage, image updates, repositions the fragment projection on to each virtual imaging plane in real time during fracture reduction and osteosynthesis using an OpenGL-based texture warping. Combined with a photorealistic virtual implant model rendering technique, the present technique allows the control of a closed indirect fracture osteosynthesis in the real world through direct insight into the virtual world. The first clinical study results show the reduction in the X-ray radiation to the patient as well as to the surgical team, and the improved operative precision, guaranteeing more safety for the patient. Furthermore, based on the experiences gained from this clinical study, two technical enhancements are proposed. One focuses on eliminating the user interactions with automated identifications and segmentations of bone fragments. The other focuses on providing non-photorealistic implant visualization. Further experiments are performed to validate the effectiveness of the proposed enhancements.     

融合五自由度位姿信息的单目内窥镜目标尺寸测量

针对低分辨率、弱纹理、缺少参照物的小场景下内窥镜图像目标测量困难问题,提出了融合5自由度电磁传感器的单目内窥镜下目标尺寸测量方法。首先,分析了基于5自由度传感器的内窥镜定位原理,得到内窥镜沿主光轴方向的位移。接着,以结石目标为例分析了图像目标关键信息的导航采集方法,即通过语义分割网络获得图像目标的轮廓信息,进而与内窥镜主光轴进行重合度判定,记录符合重合条件关键帧的图像目标长度信息与对应的位姿信息。最后,基于针孔相机成像模型,将目标成像比例关系与内窥镜沿主光轴的位移结合,建立了目标尺寸测量方法。实验结果表明：所提方法的测量误差控制在10%以内;对长度1～9 mm目标的平均测量误差为0.33 mm。能够满足单目内窥镜检查中对目标尺寸测量的稳定可靠、精度高、省时省力等需求。     

Constraint factor graph cut–based active contour method for automated cellular image segmentation in RNAi screening

Image‐based, high throughput genome‐wide RNA interference (RNAi) experiments are increasingly carried out to facilitate the understanding of gene functions in intricate biological processes. Automated screening of such experiments generates a large number of images with great variations in image quality, which makes manual analysis unreasonably time‐consuming. Therefore, effective techniques for automatic image analysis are urgently needed, in which segmentation is one of the most important steps. This paper proposes a fully automatic method for cells segmentation in genome‐wide RNAi screening images. The method consists of two steps: nuclei and cytoplasm segmentation. Nuclei are extracted and labelled to initialize cytoplasm segmentation. Since the quality of RNAi image is rather poor, a novel scale‐adaptive steerable filter is designed to enhance the image in order to extract long and thin protrusions on the spiky cells. Then, constraint factor GCBAC method and morphological algorithms are combined to be an integrated method to segment tight clustered cells. Compared with the results obtained by using seeded watershed and the ground truth, that is, manual labelling results by experts in RNAi screening data, our method achieves higher accuracy. Compared with active contour methods, our method consumes much less time. The positive results indicate that the proposed method can be applied in automatic image analysis of multi‐channel image screening data.     

基于PLC控制的变送器自动测漏系统的研究

在变送器的生产线上,变送器的泄漏检测是一道很重要的工序.在检测过程中,由于仪器精度以及人工操作等因素会使得检测结果有一定的偏差.介绍了常用的气泡检测法,并在气泡检测法的基础上考虑实际应用,设计出一套全自动变送器测漏系统.通过计算确定了机械手的型号,介绍了机械手在检测系统中的基本工作过程,并详细阐明了PLC的控制原理,给出了PLC控制系统的I/O原理图.基于传统的水检法,整合了现代技术,采用机械手来抓取变送器,并利用摄像头拍摄的信息判断变送器是否有泄漏,整个过程都由PLC来控制,基本实现了检测过程的自动化.     

Stewart平台动态位姿立体视觉检测中的图像处理

本文提出采用立体视觉检测Ｓｔｅｗａｒｔ平台动态位姿,并着重研究其中的图像处理部分。     

基于图像处理的钢卷尺自动检定系统

针对钢卷尺现有检定方法劳动强度大、效率较低的问题,提出了基于数字图像处理的自动检测新方法,用CCD摄像机对标准和被测钢卷尺每米处的图像进行采集,利用Visual Basic 6.0编写了图像处理软件,阐述了该系统的总体结构和实现方法,同时给出了该系统的部分通信软件,详细介绍了图像处理方法。实际使用结果证明该系统能够按检定规程实现对钢卷尺误差的自动检测,提高了检定效率和结果的准确度。     

Automated signal pattern evaluation of a bladder cancer specific multiprobe-fish assay applying a user-trainable workstation

OBJECTIVE: Signal pattern enumeration of Urovysion Fluorescence in Situ Hybridization test is tedious and requires great experience. Our aim was to eliminate human interaction by automating the process, using an adoptable, automated image acquisition, and analysis system. METHODS: For extensive analytical analysis control, cell populations were used, while preliminary clinical study was performed on 21 patients with clinical suspicion for bladder cancer. All investigations were carried out using an automated user‐trainable workstation (Metafer4‐Metacyte). RESULTS: The system identified nuclei with a specificity and sensitivity of 92.7 and 96.6%, respectively, while signal detection accuracy was 81.1% on average. Both analytical and diagnostic accuracy of automated analysis was comparable to manual approach (94.8 and 71% vs. 97.9 and 76%, respectively), but classification accuracy increased with degree of polysomy, thus diagnostic sensitivity in low grade, low stage cases was poor. CONCLUSION: It is possible to automate signal enumeration of Urovysion using a user‐trainable system, and achieve efficiency comparable to manual analysis. Previously introduced automated immunophenotypic targeting should further increase diagnostic sensitivity, while resulting in a comprehensively automated method. However, the problem of reduced detection accuracy in cases featured with low polysomy is likely to remain a great challenge of automated signal enumeration. Microsc. Res. Tech. 75:814–820, 2012. © 2011 Wiley Periodicals, Inc.