专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US06721444B1 3-dimensional object recognition method and bin-picking system using the method 失效
标题翻译： 3维物体识别方法和采摘系统采用该方法
公开(公告)号：US06721444B1
公开(公告)日：2004-04-13
申请号：US09581550
申请日：2000-07-13
申请人： Haisong Gu , Tomoharu Nakahara , Hidekazu Araki , Hiroyuki Fujii
发明人： Haisong Gu , Tomoharu Nakahara , Hidekazu Araki , Hiroyuki Fujii
IPC分类号： G06K900
CPC分类号： B25J9/1697 , G05B2219/40053 , G06T7/74 , G06T7/97
摘要： A 3-dimensional object recognition method, by use of which three-dimensional position and posture of an object can be accurately recognized at high speed, comprises the steps of (A) taking a pair of first and second images for making a stereo image of the object; (B) detecting a two-dimensional feature of the object on each of the first and second images; (C) evaluating a degree of reliability of the result of the step (B) by comparing with a model data of the object; (D) making a correspondence of the two-dimensional feature between the first and second images according to a stereoscopic measurement principle; (E) evaluating a degree of reliability of the result of the step (D) by comparing the two-dimensional feature detected on the first image with the corresponding two-dimensional feature detected on the second image; (F) recognizing the three-dimensional position and posture of the object according to information in three dimensions of the two-dimensional feature obtained by the correspondence; and (G) evaluating a degree of reliability of the recognized three-dimensional position and posture. It is preferred to use the 3-dimensional object recognition method to a bin-picking system for picking up an article from a bin, in which a plurality of articles are heaped up in confusion, and carrying the picked-up article to a required position.
摘要翻译：通过使用能够高速准确识别对象的三维位置和姿势的三维物体识别方法，包括以下步骤：（A）拍摄一对第一和第二图像以使立体图像成为物体; （B）在所述第一和第二图像中的每一个上检测所述对象的二维特征; （C）通过与对象的模型数据进行比较来评估步骤（B）的结果的可靠性程度; （D）根据立体测量原理对第一和第二图像之间的二维特征进行对应; （E）通过将在第一图像上检测到的二维特征与在第二图像上检测到的对应的二维特征进行比较来评估步骤（D）的结果的可靠性程度; （F）根据通过对应获得的二维特征的三维信息，识别物体的三维位置和姿势; 和（G）评估所识别的三维位置和姿势的可靠度。优选的是，将三维物体识别方法用于拾取拾取系统，用于从垃圾箱拾取物品，其中多个物品混淆堆积，并将拾取的物品运送到所需位置。

2. 发明授权

US5692061A Method of utilizing a two-dimensional image for detecting the position, posture, and shape of a three-dimensional objective 失效
标题翻译：利用二维图像检测三维物镜的位置，姿势和形状的方法
公开(公告)号：US5692061A
公开(公告)日：1997-11-25
申请号：US391006
申请日：1995-02-21
申请人： Katsuhiro Sasada , Tomoharu Nakahara , Hidekazu Araki
发明人： Katsuhiro Sasada , Tomoharu Nakahara , Hidekazu Araki
IPC分类号： G06T1/00 , G06K9/00 , G06T7/00
CPC分类号： G06T7/0046 , G06K9/00201 , G06T7/0051
摘要： A method for recognizing a three-dimensional objective in which a two-dimensional image is obtained from the same viewing point as a distance image obtained by picking up the objective in a three-dimensional space and the two-dimensional image is utilized to previously limit an existence zone of the objective under detection for the distance image and to perform objective detecting operation over the partial distance image in the limited zone, thereby realizing a sufficiently high speed detection of, in particular, the three-dimensional objective.
摘要翻译：一种用于识别三维物镜的方法，其中从与通过拾取三维空间中的物镜获得的距离图像相同的视点获得二维图像，并且二维图像被用于预先限定对距离图像进行检测的目标的存在区域，并且在受限区域中对部分距离图像执行目标检测操作，从而实现特别是三维目标的足够高的速度检测。

3. 发明授权

US5867592A Method of utilizing edge images of a circular surface for detecting the position, posture, and shape of a three-dimensional objective having the circular surface part 失效
标题翻译：利用圆形表面的边缘图像检测具有圆形表面部分的三维物镜的位置，姿势和形状的方法
公开(公告)号：US5867592A
公开(公告)日：1999-02-02
申请号：US907161
申请日：1997-08-06
申请人： Katsuhiro Sasada , Tomoharu Nakahara , Hidekazu Araki
发明人： Katsuhiro Sasada , Tomoharu Nakahara , Hidekazu Araki
IPC分类号： G06T1/00 , G06K9/00 , G06T7/00 , G06K9/46
CPC分类号： G06T7/0046 , G06K9/00201 , G06T7/0051
摘要： A method for recognizing a three-dimensional objective in which a two-dimensional image is obtained from the same viewing point as a distance image obtained by picking up the objective in a three-dimensional space and the two-dimensional image is utilized to previously limit an existence zone of the objective under detection for the distance image and to perform objective detecting operation over the partial distance image in the limited zone, thereby realizing a sufficiently high speed detection of, in particular, the three-dimensional objective.
摘要翻译：一种用于识别三维物镜的方法，其中从与通过拾取三维空间中的物镜获得的距离图像相同的视点获得二维图像，并且二维图像被用于预先限定对距离图像进行检测的目标的存在区域，并且在受限区域中对部分距离图像执行目标检测操作，从而实现特别是三维目标的足够高的速度检测。

4. 发明授权

US07684894B2 Autonomously moving robot 有权
标题翻译：自动移动机器人
公开(公告)号：US07684894B2
公开(公告)日：2010-03-23
申请号：US10549110
申请日：2004-03-12
申请人： Tatsuo Sakai , Tomoharu Nakahara , Hitoshi Kitano , Yukihiko Kitano , Tsuyoshi Yamane , Hiroyuki Fujii
发明人： Tatsuo Sakai , Tomoharu Nakahara , Hitoshi Kitano , Yukihiko Kitano , Tsuyoshi Yamane , Hiroyuki Fujii
IPC分类号： G06F19/00
CPC分类号： G05D1/0246
摘要： An autonomously moving robot that drives while evading an obstacle by an environment information acquisitioner. The information acquisitioner includes an imager that takes an image of a circumference on a driving route, an image recognition processor that extracts an area having a property relating to a region of a human body, a ranger that measures a range and an orientation to an object existing in the circumference on the driving route, a range information analyzer that obtains a shape of the object, and an environment recognizer that recognizes the environment information on the driving route. The environment recognizer compares the area extracted in the image recognition processor with the object recognized in the range information analyzer, and recognizes the object as a person when both of them agree with each other.
摘要翻译：一种自动移动的机器人，在环境信息采集器避开障碍物的同时驱动。该信息获取装置包括拍摄驾驶路线周围的图像的图像摄像机，提取与人体的区域有关的属性的区域的图像识别处理器，测量对象的范围和取向的游标者存在于驾驶路线的圆周上，获取对象的形状的范围信息分析器和识别驾驶路线的环境信息的环境识别器。环境识别器将图像识别处理器中提取的区域与范围信息分析器中识别的对象进行比较，并且当对象彼此一致时将该对象识别为人。

5. 发明申请

US20060184274A1 Autonomously moving robot 有权
标题翻译：自动移动机器人
公开(公告)号：US20060184274A1
公开(公告)日：2006-08-17
申请号：US10549110
申请日：2004-03-12
申请人： Tatsuo Sakai , Tomoharu Nakahara , Hitoshi Kitano , Yukihiko Kitano , Tsuyoshi Yamane , Hiroyuki Fujii
发明人： Tatsuo Sakai , Tomoharu Nakahara , Hitoshi Kitano , Yukihiko Kitano , Tsuyoshi Yamane , Hiroyuki Fujii
IPC分类号： G06F19/00
CPC分类号： G05D1/0246
摘要： An autonomously moving robot drives while evading an obstacle by recognizing the obstacle and self-location by an environment information acquisitioner. The information acquisitioner comprises an imager that takes an image of a circumference on a driving route, an image recognition processor that extracts an area having a property relating to a region of a human body by arithmetically processing the photographed image, a ranger that measures a range and an orientation to an object existing in the circumference on the driving route, a range information analyzer that obtains a shape of the object by arithmetically processing the obtained range information and recognizing that the object is a candidate of a person, and an environment recognizer that recognizes the environment information on the driving route. The environment recognizer compares an orientation of an area having the property extracted in the image recognition processor with an orientation of the object recognized as the candidate of a person in the range information analyzer, and recognize the object as a person when both of them agree with reach other. Thereby, the autonomously moving robot drives safely and smoothly corresponding to the obstacle by judging what the obstacle is.
摘要翻译：自动移动机器人通过识别环境信息获取器的障碍物和自身位置来避开障碍物。信息获取器包括拍摄驾驶路线上的圆周图像的图像摄像机，通过对拍摄图像进行算术处理来提取与人体的区域有关的属性的区域的图像识别处理器，测量范围以及对于存在于驾驶路线上的圆周中的物体的取向，范围信息分析器，其通过对获得的范围信息进行算术处理并且识别出该对象是人的候选者来获得对象的形状;以及环境识别器，识别驾驶路线上的环境信息。环境识别器将具有在图像识别处理器中提取的属性的区域的方位与在范围信息分析器中被识别为人的候选的对象的方位进行比较，并且当两者都同意时将该对象识别为人到达其他因此，通过判断障碍物是什么，自主运动的机器人能够安全平稳地对应于障碍物。

6. 发明申请

US20140043444A1 STEREO CAMERA DEVICE AND COMPUTER-READABLE RECORDING MEDIUM 审中-公开
标题翻译：立体相机设备和计算机可读记录介质
公开(公告)号：US20140043444A1
公开(公告)日：2014-02-13
申请号：US14113975
申请日：2012-05-30
申请人： Kazuma Haraguchi , Nobuhiro Miichi , Tomoharu Nakahara
发明人： Kazuma Haraguchi , Nobuhiro Miichi , Tomoharu Nakahara
IPC分类号： H04N13/02
CPC分类号： H04N13/239 , G01B11/03 , G01C3/085 , G06T3/0062 , G06T7/593 , G06T2207/10012 , H04N13/296 , H04N2013/0081
摘要： The stereo camera device includes: a pair of cameras; a first converter converting images of the cameras into first conversion images; a second converter converting the images into second conversion images; and a disparity estimation unit. The first conversion image is an image in which positions of pixels are represented by two-dimensional orthogonal coordinates defined by a first angle around a first axis defined by a straight line connecting optical centers of the cameras and a second angle around a second axis defined by an optical axis of the camera. The second conversion image is an image in which positions of pixels are represented by two-dimensional orthogonal coordinates defined by the first angle and a third angle around a third axis orthogonal to the first and second axes. The disparity estimation unit calculates a disparity of a desired point in a space based on the first and second conversion images.
摘要翻译：立体相机装置包括：一对相机; 将相机的图像转换成第一转换图像的第一转换器; 将图像转换成第二转换图像的第二转换器; 和视差估计单元。第一转换图像是其中像素的位置由通过由连接照相机的光学中心的直线限定的第一轴围绕第一角度限定的二维正交坐标和围绕第二轴定义的第二角度的第二角度相机的光轴。第二转换图像是其中像素的位置由由第一角度定义的二维正交坐标和围绕与第一和第二轴正交的第三轴的第三角度表示的图像。视差估计单元基于第一和第二转换图像来计算空间中的期望点的视差。

7. 发明申请

US20140222230A1 ENERGY MANAGEMENT DEVICE AND PROGRAM 审中-公开
标题翻译：能源管理设备和计划
公开(公告)号：US20140222230A1
公开(公告)日：2014-08-07
申请号：US14343978
申请日：2012-09-04
申请人： Noriyoshi Shimizu , Takashi Nishiyama , Tomoharu Nakahara
发明人： Noriyoshi Shimizu , Takashi Nishiyama , Tomoharu Nakahara
IPC分类号： G05B13/02
CPC分类号： G05B13/02 , G06Q50/06 , H02J3/14 , H02J9/005 , H02J13/002 , H02J2003/003 , H02J2003/143 , Y02B70/3225 , Y02B70/3233 , Y02B70/3266 , Y02B90/2615 , Y04S20/222 , Y04S20/225 , Y04S20/242 , Y04S40/121
摘要： Acquiring unit acquires, as power usage amount, amount of power for each measurement time, for each of branch lines through which power is fed to electrical loads, respectively. History storage unit stores a plurality of power usage amounts for each branch line so that each amount is made to correspond to time and date when acquired. Analyzing unit calculates frequency distribution of magnitudes of power usage amounts during target period, of the plurality of power usage amounts in history storage unit, and estimates that power usage amount in which cumulative relative frequency from lower limit of power usage amount is frequency threshold or more is amount of standby power. Analyzing unit determines whether electrical load corresponding to each branch line is in operation by setting standby power to reference value and comparing reference value with magnitude of power usage amount. Determined result is displayed on display device.
摘要翻译：获取单元分别为每个测量时间的功率量，作为功率使用量，分别向电力负载馈送电力的每条支线。历史存储单元存储每个分支线的多个功率使用量，使得每个量对应于获取时的时间和日期。分析单元计算历史存储单元中的多个功率使用量的目标周期内的功率使用量的频率分布，并且估计来自使用量的下限的累积相对频率为频率阈值以上的功率使用量是待机功率的数量。分析单元通过将待机功率设置为参考值，并将参考值与功率使用量的大小进行比较来确定与每个分支线对应的电气负载是否在运行。确定的结果显示在显示设备上。

8. 发明授权

US4974261A Optical surface inspection method 失效
标题翻译：光学表面检测方法
公开(公告)号：US4974261A
公开(公告)日：1990-11-27
申请号：US433823
申请日：1989-11-09
申请人： Tomoharu Nakahara , Shinji Hatazawa , Shozo Nomura , Toshinori Inoue , Mitsuru Shirasawa , Satoshi Yamatake
发明人： Tomoharu Nakahara , Shinji Hatazawa , Shozo Nomura , Toshinori Inoue , Mitsuru Shirasawa , Satoshi Yamatake
IPC分类号： G01N21/88 , G01N21/956
CPC分类号： G06K9/4609 , G01N21/88 , G06K9/4638 , G01N21/956
摘要： An optical surface inspection method inspects a surface defect such as a crack, stain, and irregularity of an article, based upon an original grey value image of two dimensional configuration of the article and also upon an edge image representing a border line of the article surface. An area confined by the border line in the edge picture image is scanned for an edge which may be indicative of the defect. The pixel detected to have the edge is marked as a flag point. A plurality of pixels in the vicinity of the flag point are selected to be arranged in a direction generally perpendicular to the edge direction so that the selected pixels are evaluated in terms of their grey values whether there is a critical change between the selected pixels. When the critical change is acknowledged, the scanned edge is judged to be a clear transition between two contrasted regions and thus indicative of a defect.
摘要翻译：光学表面检查方法基于物品的二维构造的原始灰度值图像以及表示物品表面的边界线的边缘图像检查诸如物品的裂纹，污点和不规则性的表面缺陷。对边缘图像中的边界线限制的区域被扫描可能指示缺陷的边缘。检测到具有边缘的像素被标记为标志点。选择在标记点附近的多个像素沿着大致垂直于边缘方向的方向布置，使得根据灰度值来评估所选择的像素是否在所选择的像素之间存在临界变化。当确定临界变化时，扫描的边缘被判定为两个对比区域之间的清晰过渡，并因此指示缺陷。

9. 发明授权

US4677473A Soldering inspection system and method therefor 失效
标题翻译：焊接检查系统及其方法
公开(公告)号：US4677473A
公开(公告)日：1987-06-30
申请号：US795912
申请日：1985-11-07
申请人： Shinji Okamoto , Kazunari Yoshimura , Tomoharu Nakahara
发明人： Shinji Okamoto , Kazunari Yoshimura , Tomoharu Nakahara
IPC分类号： G01B11/24 , B23K1/00 , G01N21/88 , G01N21/956 , H04N7/18 , F21V33/00
CPC分类号： G01N21/95684 , G01N21/8806 , G01N2021/4742 , G01N2021/95638 , G01N21/8851
摘要： A soldering inspection system wherein light is irradiated on a soldered part at different incident angles by a light emitting means to collect information indicative of three-dimensional configuration of the soldered part and discriminate whether or not the configuration is acceptable. The three-dimensional configurational information can be obtained with light irradiated at least from two positions mutually of different angles with respect to the soldered part, the inspection is thereby made from quantitative viewpoint, and a highly precise result of the inspection is obtainable.
摘要翻译：一种焊接检查系统，其中通过发光装置以不同的入射角将光照射在焊接部件上，以收集指示焊接部件的三维构造的信息，并且判别该构造是否可接受。可以通过至少从相对于焊接部分的不同角度的两个位置照射的光获得三维结构信息，从而从定量的角度进行检查，并且可以获得高度精确的检查结果。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式