利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

24 条记录 (耗时 0.015 秒)

    Method for monitoring equipment state by distribution measurement data, and equipment monitoring apparatus
    2.
    发明授权
    Method for monitoring equipment state by distribution measurement data, and equipment monitoring apparatus 失效

    公开(公告)号：US5822450A

    公开(公告)日：1998-10-13

    申请号：US519894

    申请日：1995-08-28

    申请人： Akio Arakawa ,  Hideyuki Tsurumaki ,  Yoshiaki Hattori ,  Shigeru Kanemoto ,  Ichiro Tai ,  Riyoko Haneda

    发明人： Akio Arakawa ,  Hideyuki Tsurumaki ,  Yoshiaki Hattori ,  Shigeru Kanemoto ,  Ichiro Tai ,  Riyoko Haneda

    IPC分类号： G06T7/00 ,  G06K9/00

    CPC分类号： G06T7/0006 ,  G06T2207/20136 ,  G06T2207/30164

    摘要： A method for monitoring equipment state by distribution measurement data comprises: the steps of momentarily taking in two-dimensional distribution measurement data relating to the state of equipments including an equipment to be monitored; allowing the two-dimensional distribution measurement data and a display result by a three-dimensional shape model of the equipment to be monitored to undergo positioning and carrying out overlaid display in such a manner that they are caused to correspond to each other; designating an equipment portion to be inspected from the display content; allowing measurement data of the equipment to be monitored to undergo mapping onto the three-dimensional shape model corresponding to the designated equipment portion; and detecting changes in the measurement data to judge presence or absence of unusual condition of the equipment. Moreover, an equipment state monitoring apparatus comprises: a distribution measurement unit for measuring distribution of temperature, vibration or sound, etc. at the plant equipment surface; a distribution measurement image data positioning unit for determining position and direction of the distribution measurement unit in order to allow distribution measurement image data from the distribution measurement unit to undergo positioning so that it is in correspondence with a projection chart of a corresponding plant equipment spatial shape model; a texture-mapping unit for allowing the distribution measurement image data to undergo texture-mapping onto the surface of the spatial shape model of the plant equipment on the basis of the position and the direction of the measurement unit determined by the distribution measurement image data positioning unit; a projecting unit for describing a projection chart of the texture-mapped plant equipment spatial shape model; and an image display unit for displaying the projection chart from the projecting unit.

    Method of detecting edges in images
    4.
    发明授权
    Method of detecting edges in images 失效
    检测图像边缘的方法

    公开(公告)号：US5073958A

    公开(公告)日：1991-12-17

    申请号：US556782

    申请日：1990-07-11

    申请人： Martin W. Imme

    发明人： Martin W. Imme

    IPC分类号： H04N5/14 ,  G01R33/56 ,  G06T5/00 ,  G06T7/60 ,  G09G5/00 ,  H04N5/262

    CPC分类号： G06T7/0083 ,  G01R33/56 ,  G06T2207/10116 ,  G06T2207/20136

    摘要： An image matrix of an image to be filtered is scanned in four different directions, i.e. row-wise, column-wise and also in the two diagonal directions, and in all pixel sequences scanned local maxima and minima are determined. From these values the actual grey-level variation in the non-filtered image is approximated by way of a function which includes an inflection point, for example a sine function. The approximation is realized, for example, according to the least error squares method; the inflection point indicates a point of an edge. interruptions in the course of the edges as well as shifts with respect to the actual image are thus avoided.

    摘要翻译： 要扫描的图像的图像矩阵在四个不同的方向上扫描，即逐行，逐列和也在两个对角线方向上，并且确定所扫描的局部最大值和最小值的所有像素序列。 从这些值中，未滤波图像中的实际灰度级变化通过包括拐点（例如正弦函数）的函数来近似。 例如，根据最小误差平方法实现近似; 拐点表示边缘的一点。 因此避免了在边缘过程中的中断以及相对于实际图像的偏移。

    Method of processing image data on crack
    5.
    发明授权
    Method of processing image data on crack 失效
    破解图像数据的方法

    公开(公告)号：US5046115A

    公开(公告)日：1991-09-03

    申请号：US378522

    申请日：1989-06-22

    申请人： Tatsuya Maruyama ,  Toshihiko Fukuhara

    发明人： Tatsuya Maruyama ,  Toshihiko Fukuhara

    IPC分类号： G06K9/46 ,  G06T7/00

    CPC分类号： G06T7/60 ,  G06K9/4638 ,  G06T7/0006 ,  G06T2207/20136 ,  G06T2207/30256

    摘要： The present invention is concerned with an automatic recognition of image data representative of crack derived from measurements of the road surface using a computor (4). An image memory in which data on the road surface are stored is divided into a plurality of regions and the region constituting a part of the divided regions for which a determination has been made such that crack (LP) is existent is utilized as a start point for a pursuing operation. A series of processings of pursuit and extraction such as extracting line segments (SG) corresponding to the crack (LP) from the start point region, making a determination on the direction of pursuing to be next effected on the basis of the line direction (.theta.) of the extracted line segments (SG), making a determination as to whether or not crack (LP) is existent in the adjacent divided regions situated in the direction of pursuing and performing a processing of extracting line segments (SG) only in the region for which a determination has been made such that crack (LP) is existent are repeatedly exeuted at every start point until pursuing is terminated. This permits data representative of the crack in the image memory to be extracted in the form of a combination among the line segments (SG). Thus, extraction of line segments is not required in all the divided regions. Consequently, a processing speed can be increased.

    摘要翻译： 使用计算机（4）以自动方式识别表示在路面上检测到的裂纹的数据。 存储路面数据的图像存储器被分成多个区域。 这些区域中的一些数据表示裂纹（LP），并且它们中的任何一个可以是跟踪的起始点。 从开始区域提取与裂纹（LP）对应的线段（SG）。 基于所提取的线段（SG）的线（θ）的方向确定下一个跟踪方向，并且确定在跟踪方向上的相邻区域中是否存在裂纹（LP）。 分段（SG）仅从已被发现含有裂纹（LP）的区域提取。 该过程在每个起点开始并重复，直到跟踪完成。 因此，提取图像存储器中的裂纹数据作为线段（SG）的组合。 在该方法中，不一定从所有区域提取段，因此处理速度增加。

    System and method for ranking and extracting salient contours for target recognition
    6.
    发明授权
    System and method for ranking and extracting salient contours for target recognition 失效
    用于评估和提取目标识别突出轮廓的系统和方法

    公开(公告)号：US5566246A

    公开(公告)日：1996-10-15

    申请号：US483351

    申请日：1995-06-07

    申请人： Kashi Rao

    发明人： Kashi Rao

    IPC分类号： G06T7/60 ,  G06T5/00 ,  G06K9/00

    CPC分类号： G06K9/3241 ,  G06K9/4604 ,  G06K9/4609 ,  G06K9/4671 ,  G06T7/0083 ,  G06T2207/10016 ,  G06T2207/10032 ,  G06T2207/10048 ,  G06T2207/20016 ,  G06T2207/20136 ,  G06T2207/30212

    摘要： A system and method for obtaining salient contours from two-dimensional images acquired by a sensor is disclosed which process the two-dimensional images with an edge detector to produce edgels from each of the images, link the edgels into lists known as contours, compute a saliency value for each of the contours, rank the contours in decreasing order of saliency, and select certain ones of the ranked contours based on the requirements of a particular vision application.Other devices, systems and methods are also disclosed.

    摘要翻译： 公开了一种用于从由传感器获取的二维图像获得显着轮廓的系统和方法，其利用边缘检测器处理二维图像以从每个图像产生边缘，将边缘链接成称为轮廓的列表，计算 每个轮廓的显着性值，以显着性的降序排列轮廓，并且基于特定视觉应用​​的要求来选择某些等级轮廓。 还公开了其他装置，系统和方法。

    Linear pattern recognizing method
    9.
    发明授权
    Linear pattern recognizing method 失效
    线性模式识别方法

    公开(公告)号：US5181258A

    公开(公告)日：1993-01-19

    申请号：US465232

    申请日：1990-03-14

    申请人： Makoto Nagao ,  Keiji Terada

    发明人： Makoto Nagao ,  Keiji Terada

    IPC分类号： G06K9/46 ,  G06T7/00

    CPC分类号： G06K9/4647 ,  G06T7/60 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/20068 ,  G06T2207/20136 ,  G06T2207/30256

    摘要： Disclosed is a linear pattern recognizing method of recognizing a linear pattern included in the image data stored in an original image memory. The memory region of the original image memory is divided into a plurality of smaller regions, and the image data of the smaller regions are utilized to obtain projection waveforms at a plurality of projection angles for each smaller region. The projection waveforms thus obtained are analyzed to detect the presence or absence, line direction (.theta.), smaller region. According to the results of detection, a linear segment corresponding to the linear pattern is extracted for each smaller region.

    摘要翻译： 识别包含在存储在原始视频存储器中的视频数据中的线性模式的方法。 原始视频存储器的存储区域被划分为多个区域，从分区的视频数据中找出每个区域的多个不同投影角度的投影波形，分析投影波形以确定存在 或不存在任何线性图案，每个分割线中的线的方向（θ），线宽（W）和线长度（L），并且对于每个分割线，对应于线性图案的线段基于 结果确定。

    Method for inspecting the leads of electrical components on surface mount printed circuit boards
    10.
    发明授权
    Method for inspecting the leads of electrical components on surface mount printed circuit boards 失效
    用于检查表面贴装印刷电路板上电气元件引线的方法

    公开(公告)号：US5023916A

    公开(公告)日：1991-06-11

    申请号：US399688

    申请日：1989-08-28

    申请人： Heinz Breu

    发明人： Heinz Breu

    IPC分类号： G01R31/04 ,  B23K31/12 ,  G01N21/956 ,  G06T1/00 ,  G06T7/00 ,  H05K3/34 ,  H05K13/08

    CPC分类号： G06T7/001 ,  B23K31/12 ,  G01N21/95684 ,  H05K13/08 ,  G06T2207/20136 ,  G06T2207/30152

    摘要： A method of inspecting solder joints that connect surface-mount electronic components to printed circuit boards is provided. Preferably, the method includes the steps of obtaining an image of a plurality of the leads of the electronic component, for each obtained image, representing segments of the image that correspond to each of the leads by polygons, projecting pixel intensity values within each polygon each onto an axial dimension to provide a measured waveform, comparing the measured waveform for each lead with a corresponding model waveform, and, classifying each lead as being either satisfactory or unsatisfactory on the basis of said comparisons.

    摘要翻译： 提供了一种检查将表面贴装电子部件连接到印刷电路板的焊点的方法。 优选地，该方法包括以下步骤：对于每个获得的图像，获得电子部件的多个引线的图像，表示通过多边形对应于每个引线的图像的段，在每个多边形内投影像素强度值 在轴向尺寸上提供测量波形，将每个引线的测量波形与相应的模型波形进行比较，并且根据所述比较将每个引线分类为满意的或不令人满意的。