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

US08320679B2 Method for detecting objects using flexible edge arrangements 有权
标题翻译：使用柔性边缘布置检测物体的方法
公开(公告)号：US08320679B2
公开(公告)日：2012-11-27
申请号：US12052864
申请日：2008-03-21
申请人： Yan Li , Yanghai Tsin , Yakup Genc
发明人： Yan Li , Yanghai Tsin , Yakup Genc
IPC分类号： G06K9/62
CPC分类号： G06K9/4609
摘要： A method wherein images of different types of objects within a class are partitioned into region stacks. For each one of the stacks, the method: (a) applies a template to extract fragments having a predetermined size and one of a plurality of different spatial orientations, to generate extracted templates; (b) determines, from the extracted templates, a most frequent one thereof having only a first number of fragments with a common spatial orientations; (c) records the number of images having the determined most frequent extracted template; (d) repeats (b) and (c) with successively increasing number of fragments until the number of recoded images falls below a threshold; and (e) selects as a master extracted template the one of the most frequent templates having the largest recorded number of fragments. The master extracted templates for the stacks are combined into a map that is then compared with background images to remove extracted templates matching segment in the background.
摘要翻译：将类内不同类型对象的图像分割成区域堆栈的方法。对于堆叠中的每一个，方法：（a）应用模板来提取具有预定大小和多个不同空间取向之一的片段，以产生提取的模板; （b）从所提取的模板中确定其中最频繁的模板具有仅具有公共空间取向的第一数量的片段; （c）记录具有确定的最频繁提取的模板的图像的数量; （d）重复（b）和（c），连续增加片段数，直到重新编码的图像数量低于阈值; 和（e）选择具有最大记录数量片段的最频繁模板之一作为主提取模板。将提取的模板用于堆栈组合成一个映射，然后将其与背景图像进行比较，以删除在后台匹配段的提取模板。

2. 发明申请

US20080260261A1 METHOD FOR DETECTING OBJECTS USING FLEXIBLE EDGE ARRANGEMENTS 有权
标题翻译：使用柔性边缘安排来检测物体的方法
公开(公告)号：US20080260261A1
公开(公告)日：2008-10-23
申请号：US12052864
申请日：2008-03-21
申请人： Yan Li , Yanghai Tsin , Yakup Genc
发明人： Yan Li , Yanghai Tsin , Yakup Genc
IPC分类号： G06K9/62
CPC分类号： G06K9/4609
摘要： A method wherein images of different types of objects within a class are partitioned into region stacks. For each one of the stacks, the method: (a) applies a template to extract fragments having a predetermined size and one of a plurality of different spatial orientations, to generate extracted templates; (b) determines, from the extracted templates, a most frequent one thereof having only a first number of fragments with a common spatial orientations; (c) records the number of images having the determined most frequent extracted template; (d) repeats (b) and (c) with successively increasing number of fragments until the number of recoded images falls below a threshold; and (e) selects as a master extracted template the one of the most frequent templates having the largest recorded number of fragments. The master extracted templates for the stacks are combined into a map that is then compared with background images to remove extracted templates matching segment in the background.
摘要翻译：将类内不同类型对象的图像分割成区域堆栈的方法。对于堆叠中的每一个，方法：（a）应用模板来提取具有预定大小和多个不同空间取向之一的片段，以产生提取的模板; （b）从所提取的模板中确定其中最频繁的模板具有仅具有公共空间取向的第一数量的片段; （c）记录具有确定的最频繁提取的模板的图像的数量; （d）重复（b）和（c），连续增加片段数，直到重新编码的图像数量低于阈值; 和（e）选择具有最大记录数量片段的最频繁模板之一作为主提取模板。将提取的模板用于堆栈组合成一个映射，然后将其与背景图像进行比较，以删除在后台匹配段的提取模板。

3. 发明申请

US20060188131A1 System and method for camera tracking and pose estimation 有权
标题翻译：摄像机跟踪和姿态估计的系统和方法
公开(公告)号：US20060188131A1
公开(公告)日：2006-08-24
申请号：US11359673
申请日：2006-02-22
申请人： Xiang Zhang , Yakup Genc , Visvanathan Ramesh , Yanghai Tsin
发明人： Xiang Zhang , Yakup Genc , Visvanathan Ramesh , Yanghai Tsin
IPC分类号： G06K9/00
CPC分类号： G06T7/246 , G06T7/74
摘要： A method of tracking a pose of a moving camera includes receiving a first image from a camera, receiving a sequence of digitized images from said camera, recording, for each of said sequence of digitized images, the pose and 2D correspondences of landmarks, reconstructing a location and appearance of a 2-dimensional texture patch from 2D correspondences of the landmarks by triangulation and optimization, computing back-projection errors by comparing said reconstructed texture patch with said first received image; and reconstructing said location and appearance of said 2-dimensional texture patch from the 2D correspondences of the landmarks of said sequence of digitized images by triangulation and optimization after eliminating those landmarks with large back-projection errors.
摘要翻译：跟踪移动摄像机的姿态的方法包括：从相机接收第一图像，从所述照相机接收数字化图像序列，针对所述数字化图像序列中的每一个记录地标的姿态和2D对应，重建通过三角测量和优化从地标的2D对应的二维纹理贴片的位置和外观，通过将所述重建纹理贴片与所述第一接收图像进行比较来计算反投影误差; 以及通过三角测量和优化，从所述数字化图像序列的地标的二维对应中重建所述二维纹理补片的所述位置和外观，并且消除了具有大的反投影误差的这些地标。

4. 发明授权

US07616807B2 System and method for using texture landmarks for improved markerless tracking in augmented reality applications 有权
标题翻译：用于在增强现实应用中使用纹理地标改进无标记跟踪的系统和方法
公开(公告)号：US07616807B2
公开(公告)日：2009-11-10
申请号：US11359673
申请日：2006-02-22
申请人： Xiang Zhang , Yakup Genc , Visvanathan Ramesh , Yanghai Tsin
发明人： Xiang Zhang , Yakup Genc , Visvanathan Ramesh , Yanghai Tsin
IPC分类号： G06K9/00 , G06K9/32 , G06T15/00
CPC分类号： G06T7/246 , G06T7/74
摘要： A method of tracking a pose of a moving camera includes receiving a first image from a camera, receiving a sequence of digitized images from said camera, recording, for each of said sequence of digitized images, the pose and 2D correspondences of landmarks, reconstructing a location and appearance of a 2-dimensional texture patch from 2D correspondences of the landmarks by triangulation and optimization, computing back-projection errors by comparing said reconstructed texture patch with said first received image; and reconstructing said location and appearance of said 2-dimensional texture patch from the 2D correspondences of the landmarks of said sequence of digitized images by triangulation and optimization after eliminating those landmarks with large back-projection errors.
摘要翻译：跟踪移动摄像机的姿态的方法包括：从相机接收第一图像，从所述照相机接收数字化图像序列，针对所述数字化图像序列中的每一个记录地标的姿态和2D对应，重建通过三角测量和优化从地标的2D对应的二维纹理贴片的位置和外观，通过将所述重建纹理贴片与所述第一接收图像进行比较来计算反投影误差; 以及通过三角测量和优化，从所述数字化图像序列的地标的二维对应中重建所述二维纹理补片的所述位置和外观，并且消除了具有大的反投影误差的这些地标。

5. 发明申请

US20050259847A1 System and method for tracking parcels on a planar surface 审中-公开
标题翻译：用于在平坦表面上跟踪包裹的系统和方法
公开(公告)号：US20050259847A1
公开(公告)日：2005-11-24
申请号：US11046717
申请日：2005-01-31
申请人： Yakup Genc , Yanghai Tsin , Cuneyt Akinlar , Anurag Mittal , Xiang Gao
发明人： Yakup Genc , Yanghai Tsin , Cuneyt Akinlar , Anurag Mittal , Xiang Gao
IPC分类号： G06K9/00 , G06T5/00 , G06T7/20
CPC分类号： G06T7/251 , G06T7/12 , G06T7/194 , G06T7/579 , G06T2207/10016 , G06T2207/20036 , G06T2207/30164
摘要： A system and method for tracking parcels on a planar surface is provided. The method comprising: acquiring an image of the parcel located on the planar surface; determining edges of the parcel; projecting the edges onto the planar surface; determining which edges belong to each side of the parcel; calculating a cost function associated with the edges belonging to each side of the parcel; searching the edges belonging to each side of the parcel to find edges having a lowest cost; and constructing a matching configuration of the parcel using the edges having the lowest cost.
摘要翻译：提供了一种用于在平面上跟踪包裹的系统和方法。该方法包括：获取位于平面上的包裹的图像; 确定包裹的边缘; 将边缘投影到平面上; 确定哪些边缘属于包裹的每一侧; 计算与属于包裹每一侧的边缘相关联的成本函数; 搜索属于包裹每一边的边缘来查找成本最低的边缘; 以及使用具有最低成本的边缘构建包裹的匹配配置。

6. 发明授权

US08212812B2 Active shape model for vehicle modeling and re-identification 有权
标题翻译：用于车辆建模和重新识别的主动形状模型
公开(公告)号：US08212812B2
公开(公告)日：2012-07-03
申请号：US12122800
申请日：2008-05-19
申请人： Yanghai Tsin , Yakup Genc , Visvanathan Ramesh
发明人： Yanghai Tsin , Yakup Genc , Visvanathan Ramesh
IPC分类号： G06T17/00
CPC分类号： G06K9/6209 , G06F17/5095 , G06K9/3241 , G06K2209/23 , G06T17/00 , G06T19/20 , G06T2210/44 , G06T2219/2021
摘要： A method for modeling a vehicle, includes: receiving an image that includes a vehicle; and constructing a three-dimensional (3D) model of the vehicle, wherein the 3D model is constructed by: (a) taking a predetermined set of base shapes that are extracted from a subset of vehicles; (b) multiplying each of the base shapes by a parameter; (c) adding the resultant of each multiplication to form a vector that represents the vehicle's shape; (d) fitting the vector to the vehicle in the image; and (e) repeating steps (a)-(d) by modifying the parameters until a difference between a fit vector and the vehicle in the image is minimized.
摘要翻译：一种用于建模车辆的方法，包括：接收包括车辆的图像; 以及构建所述车辆的三维（3D）模型，其中所述3D模型通过以下方式构造：（a）获取从车辆子集提取的预定的一组基本形状; （b）将每个基本形状乘以参数; （c）将每个乘法的结果相加以形成表示车辆形状的矢量; （d）将矢量拟合到图像中的车辆; 和（e）通过修改参数来重复步骤（a） - （d），直到图像中的拟合向量和车辆之间的差最小化。

7. 发明申请

US20080294401A1 Active Shape Model for Vehicle Modeling and Re-Identification 有权
标题翻译：车辆建模和重新识别的主动形状模型
公开(公告)号：US20080294401A1
公开(公告)日：2008-11-27
申请号：US12122800
申请日：2008-05-19
申请人： Yanghai Tsin , Yakup Genc , Visvanathan Ramesh
发明人： Yanghai Tsin , Yakup Genc , Visvanathan Ramesh
IPC分类号： G06G7/48 , G09G5/02
CPC分类号： G06K9/6209 , G06F17/5095 , G06K9/3241 , G06K2209/23 , G06T17/00 , G06T19/20 , G06T2210/44 , G06T2219/2021
摘要： A method for modeling a vehicle, includes: receiving an image that includes a vehicle; and constructing a three-dimensional (3D) model of the vehicle, wherein the 3D model is constructed by: (a) taking a predetermined set of base shapes that are extracted from a subset of vehicles; (b) multiplying each of the base shapes by a parameter; (c) adding the resultant of each multiplication to form a vector that represents the vehicle's shape; (d) fitting the vector to the vehicle in the image; and (e) repeating steps (a)-(d) by modifying the parameters until a difference between a fit vector and the vehicle in the image is minimized.
摘要翻译：一种用于建模车辆的方法，包括：接收包括车辆的图像; 以及构建所述车辆的三维（3D）模型，其中所述3D模型通过以下方式构造：（a）获取从车辆子集提取的预定的一组基本形状; （b）将每个基本形状乘以参数; （c）将每个乘法的结果相加以形成表示车辆形状的矢量; （d）将矢量拟合到图像中的车辆; 和（e）通过修改参数来重复步骤（a） - （d），直到图像中的拟合向量和车辆之间的差最小化。

8. 发明申请

US20080002909A1 Reconstructing Blurred High Resolution Images 审中-公开
标题翻译：重构模糊高分辨率图像
公开(公告)号：US20080002909A1
公开(公告)日：2008-01-03
申请号：US11695119
申请日：2007-04-02
申请人： Yanghai Tsin , Yakup Genc
发明人： Yanghai Tsin , Yakup Genc
IPC分类号： G06K9/40
CPC分类号： G06T3/403
摘要： A method of generating a resulting image includes generating a superimposed image by aligning and superimposing one or more transposed images with a reference image by using offsets of the one or more transposed images from the reference image, generating an intermediate image from the superimposed image, generating a new superimposed image by aligning and superimposing the intermediate image, the one or more transposed images and the reference image by using offsets of the one or more transposed images and the reference image from the intermediate image, and generating a resulting image from the new superimposed image.
摘要翻译：产生结果图像的方法包括通过使用来自参考图像的一个或多个转置图像的偏移量将一个或多个转置图像与参考图像对准和叠加来生成叠加图像，从叠加图像生成中间图像，产生通过使用来自中间图像的一个或多个转置图像和参考图像的偏移来对准和叠加中间图像，一个或多个转置图像和参考图像的新叠加图像，并且从新叠加的图像生成结果图像图片。

9. 发明授权

US09494532B2 System and method for side-by-side inspection of a device 有权
标题翻译：用于并排检查设备的系统和方法
公开(公告)号：US09494532B2
公开(公告)日：2016-11-15
申请号：US13240632
申请日：2011-09-22
申请人： Binglong Xie , Yakup Genc , Xiang Gao
发明人： Binglong Xie , Yakup Genc , Xiang Gao
IPC分类号： G01N21/95 , G01B11/245 , G01N21/954 , G06T7/00
CPC分类号： G01N21/9515 , G01B11/245 , G01N21/954 , G06T7/001 , G06T2200/24 , G06T2207/30164
摘要： Systems and methods for inspecting a device include arranging the device in a known position relative to a plurality of movable cameras mounted on a controllable actuator controlled by a computing device and pointed at the device by controlling the controllable actuator to position a camera with a user interface on the computing device with a display, and the display displays a virtual image from the camera into CAD model of the device and an image of the device generated by the camera in a side-by-side or in an overlay fashion or both.
摘要翻译：用于检查设备的系统和方法包括将设备布置在相对于安装在由计算设备控制的可控制致动器上的多个可移动摄像机的已知位置，并通过控制可控致动器来定位具有用户界面的摄像机在具有显示器的计算设备上，并且显示器将来自相机的虚拟图像显示为设备的CAD模型和由相机以并排或叠加方式或两者均生成的设备的图像。

10. 发明授权

US09462183B2 Trigger for blade imaging based on a controller 有权
标题翻译：基于控制器的刀片成像触发器
公开(公告)号：US09462183B2
公开(公告)日：2016-10-04
申请号：US13531658
申请日：2012-06-25
申请人： Binglong Xie , Yakup Genc , Frank Dierkes
发明人： Binglong Xie , Yakup Genc , Frank Dierkes
IPC分类号： H04N5/232 , F01D21/00 , G01N21/88 , G01N21/954
CPC分类号： H04N5/23222 , F01D21/003 , F05D2230/72 , G01N21/8806 , G01N21/8851 , G01N21/954 , G01N2021/8838
摘要： A rotating rotor in a turbine has blades attached. At least one blade is a reference blade of which a reference position is determined by a Once-Per-Rotation sensor. A camera positioned at a viewing port takes a sequence of images of all the blades during a rotation at a trigger moment determined by a controller. The controller receives a signal indicating that the reference blade passes its reference point. The controller is provided with data about the number of blades, the position of the camera and a desired dwell of an image related to the blade. The controller calculates the trigger moments and generates trigger signals to the camera. The trigger moment is adjusted for changing rotor speed by extracting a blade feature from blade images. The camera records images that are labeled and stored as image data on a storage device.
摘要翻译：涡轮机中的旋转转子具有附接的叶片。至少一个叶片是参考叶片，其参考位置由每转一次传感器确定。位于观察端口处的摄像机在由控制器确定的触发时刻的旋转期间拍摄所有叶片的一系列图像。控制器接收到指示参考刀片通过其参考点的信号。控制器提供关于刀片数量，相机的位置和与刀片相关的图像的期望驻留的数据。控制器计算触发力矩并产生相机的触发信号。通过从刀片图像中提取刀片特征来调整触发时刻以改变转子速度。照相机将已标记和存储为图像数据的图像记录在存储设备上。

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