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. 发明申请

US20180061107A1 MACHINE CREATION OF PROGRAM WITH FRAME ANALYSIS METHOD AND APPARATUS 审中-公开
公开(公告)号：US20180061107A1
公开(公告)日：2018-03-01
申请号：US15252126
申请日：2016-08-30
申请人： Intel Corporation
发明人： GLEN J. ANDERSON , DAVID I. POISNER , RAVISHANKAR IYER , MARK FRANCIS , MICHAEL E. KOUNAVIS , OMESH TICKOO
IPC分类号： G06T13/20 , G06T7/00 , A63F13/52 , A63F13/60
CPC分类号： G06T13/20 , A63F13/52 , A63F13/60 , G06T7/0022 , G06T7/0046 , G06T2207/10016 , G06T2213/08
摘要： Methods, apparatus, and systems to create, output, and use animation programs comprising keyframes, objects, object states, and programming elements. Objects, object states, and programming elements may be created through image analysis of image input. Animation programs may be output as videos, as non-linear interactive experiences, and/or may be used to control electronic actuators in articulated armatures.

2. 发明申请

US20160086332A1 LANDMARK BASED POSITIONING 有权
标题翻译：基于LANDMARK的定位
公开(公告)号：US20160086332A1
公开(公告)日：2016-03-24
申请号：US14494484
申请日：2014-09-23
申请人： Qualcomm Incorporated
发明人： Jiajian Chen , Hui Chao
IPC分类号： G06T7/00 , G06T11/00 , G06T11/20 , G06T11/40 , G06T19/20 , G06T15/00
CPC分类号： G06T7/0046 , G01C21/20 , G01C21/206 , G01C21/26 , G06T7/11 , G06T7/344 , G06T7/75 , G06T11/001 , G06T11/203 , G06T11/40 , G06T15/005 , G06T15/40 , G06T19/20 , G06T2200/04 , G06T2207/10004 , G06T2207/10032 , G06T2207/30204 , G06T2219/2004 , G06T2219/2012
摘要： Disclosed are devices, methods and storage media for use in determining position information for imaging devices or mobile devices. In some implementations, a landmark is identified in an image which is obtained from an imaging device which in turn is positioned at a location and in a pose. A virtual two-dimensional image that would be visible from the landmark is determined based, at least in part, on the pose. The location or position information is based, at least in part, on the virtual two-dimensional image.
摘要翻译：公开了用于确定成像设备或移动设备的位置信息的设备，方法和存储介质。在一些实施方案中，在从成像装置获得的图像中识别地标，该成像装置又位于位置和姿势。至少部分地基于姿势来确定从地标可见的虚拟二维图像。位置或位置信息至少部分地基于虚拟二维图像。

3. 发明申请

US20150023557A1 APPARATUS FOR RECOGNIZING OBJECTS, APPARATUS FOR LEARNING CLASSIFICATION TREES, AND METHOD FOR OPERATING SAME 有权
标题翻译：用于识别物体的装置，用于学习分类条的装置及其操作方法
公开(公告)号：US20150023557A1
公开(公告)日：2015-01-22
申请号：US14345563
申请日：2013-01-09
申请人： SAMSUNG ELECTRONICS CO., LTD.
发明人： Byung In Yoo , Chang Kyu Choi , Chang Kyo Lee , Jae Joon Han
IPC分类号： G06T7/00 , G06K9/00 , G06K9/62
CPC分类号： G06T7/0046 , G06K9/00201 , G06K9/00335 , G06K9/00362 , G06K9/469 , G06K9/6212 , G06K9/624 , G06K9/626 , G06K9/6282 , G06T7/75 , G06T15/06 , G06T15/08 , G06T15/20 , G06T15/40 , G06T17/005 , G06T2200/24 , G06T2207/10028 , G06T2207/20048 , G06T2207/20081 , G06T2207/30196
摘要： An object recognition system is provided. The object recognition system for recognizing an object may include an input unit to receive, as an input, a depth image representing an object to be analyzed, and a processing unit to recognize a visible object part and a hidden object part of the object, from the depth image, by using a classification tree. The object recognition system may include a classification tree learning apparatus to generate the classification tree.
摘要翻译：提供了一种物体识别系统。用于识别对象的对象识别系统可以包括：输入单元，用于接收表示要分析的对象的深度图像作为输入;以及处理单元，用于识别对象的可见对象部分和隐藏对象部分，深度图像，通过使用分类树。对象识别系统可以包括生成分类树的分类树学习装置。

4. 发明申请

US20150010202A1 Method for Determining Object Poses Using Weighted Features 有权
标题翻译：使用加权特征确定对象姿势的方法
公开(公告)号：US20150010202A1
公开(公告)日：2015-01-08
申请号：US13934315
申请日：2013-07-03
申请人： Mitsubishi Electric Research Laboratories, Inc.
发明人： Oncel Tuzel , Ming-Yu Liu , Yuichi Taguchi , Arvind U. Raghunathan
IPC分类号： G06T7/00 , G06K9/00
CPC分类号： G06T7/0046 , G06K9/00201 , G06T7/75 , G06T2207/10028 , G06T2207/30164
摘要： A method for determining a pose of an object in a scene by determining a set of scene features from data acquired of the scene and matching the scene features to model features to generate weighted candiate poses when the scene feature matches one of the model features, wherein the weight of the candidate pose is proportional to the model weight. Then, the pose of the object is determined from the candidate poses based on the weights.
摘要翻译：一种用于通过从场景获取的数据确定场景特征的集合来确定场景中的物体的姿态的方法，并且当场景特征与模型特征之一匹配时，将场景特征与模型特征相匹配以产生加权的烛状姿势，其中候选姿势的重量与模型重量成比例。然后，基于权重从候选姿态确定对象的姿势。

5. 发明授权

US08929614B2 Red eye detection aided by face detection 有权
标题翻译：通过脸部检测辅助红眼检测
公开(公告)号：US08929614B2
公开(公告)日：2015-01-06
申请号：US13387065
申请日：2009-10-19
申请人： Boris Oicherman , Ran Waidman , Matthew Gaubatz , Shlomo Harush
发明人： Boris Oicherman , Ran Waidman , Matthew Gaubatz , Shlomo Harush
IPC分类号： G06K9/00 , G06T7/00
CPC分类号： G06T7/0046 , G06T7/75 , G06T2207/30216
摘要： A method for identifying a pair of genuine red eye artifacts in a captured image includes the steps of determining the presence of a face in the captured image, substantially encompassing the face within a shape, and determining the presence of three or more candidate red eye artifacts within the shape. The method continues with measuring the distance from an edge of the shape to each of the three or more candidate red eye artifacts and identifying, as genuine red eye artifacts, two candidate red eye artifacts of the three or more candidate red eye artifacts that are within a predetermined vertical distance from the edge of the shape.
摘要翻译：一种用于识别拍摄图像中的一对真正的红眼伪像的方法包括以下步骤：确定拍摄图像中面部的存在，基本上包围形状中的脸部，以及确定三个或更多个候选红眼伪影的存在在形状内。该方法继续测量从形状的边缘到三个或更多个候选红眼伪像中的每一个的距离，并且将真正的红眼伪像识别为三个或更多个候选红眼伪像内的两个候选红眼伪像，距离形状的边缘的预定垂直距离。

6. 发明申请

US20140363047A1 ESTIMATOR TRAINING METHOD AND POSE ESTIMATING METHOD USING DEPTH IMAGE 有权
标题翻译：估算器训练方法和使用深度图像的估计方法
公开(公告)号：US20140363047A1
公开(公告)日：2014-12-11
申请号：US14283646
申请日：2014-05-21
申请人： SAMSUNG ELECTRONICS CO., LTD. , IMPERIAL COLLEGE
发明人： Jae Joon HAN , Danhang TANG , Tae Kyun KIM , Seung Ju HAN , Byung ln YOO , Chang Kyu CHOI , Alykhan TEJANI , Hyung Jin CHANG
IPC分类号： G06T7/00 , G06K9/62
CPC分类号： G06T7/0046 , G06K9/00382 , G06K9/00389 , G06K9/6219 , G06K9/6256 , G06K9/6259 , G06K9/627 , G06K9/6282 , G06K2209/05 , G06T7/75 , G06T2207/10028 , G06T2207/20081 , G06T2207/30196
摘要： An estimator training method and a pose estimating method using a depth image are disclosed, in which the estimator training method may train an estimator configured to estimate a pose of an object, based on an association between synthetic data and real data, and the pose estimating method may estimate the pose of the object using the trained estimator.
摘要翻译：公开了一种使用深度图像的估计器训练方法和姿态估计方法，其中估计器训练方法可以基于合成数据和实际数据之间的关联来训练被配置为估计对象的姿态的估计器，以及姿态估计方法可以使用经过训练的估计器估计对象的姿态。

7. 发明申请

US20120134546A1 RED EYE DETECTION AIDED BY FACE DETECTION 有权
标题翻译：通过脸部检测辅助的红眼检测
公开(公告)号：US20120134546A1
公开(公告)日：2012-05-31
申请号：US13387065
申请日：2009-10-19
申请人： Boris Oicherman , Ran Waidman , Matthew Gaubatz , Shlomo Harush
发明人： Boris Oicherman , Ran Waidman , Matthew Gaubatz , Shlomo Harush
IPC分类号： G06K9/00
CPC分类号： G06T7/0046 , G06T7/75 , G06T2207/30216
摘要： A method for identifying a pair of genuine red eye artifacts in a captured image includes the steps of determining the presence of a face in the captured image, substantially encompassing the face within a shape, and determining the presence of three or more candidate red eye artifacts within the shape. The method continues with measuring the distance from an edge of the shape to each of the three or more candidate red eye artifacts and identifying, as genuine red eye artifacts, two candidate red eye artifacts of the three or more candidate red eye artifacts that are within a predetermined vertical distance from the edge of the shape.
摘要翻译：一种用于识别拍摄图像中的一对真正的红眼伪像的方法包括以下步骤：确定拍摄图像中面部的存在，基本上包围形状中的脸部，以及确定三个或更多个候选红眼伪影的存在在形状内。该方法继续测量从形状的边缘到三个或更多个候选红眼伪像中的每一个的距离，并且将真正的红眼伪像识别为三个或更多个候选红眼伪像内的两个候选红眼伪像，距离形状的边缘的预定垂直距离。

8. 发明申请

US20120082341A1 IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND COMPUTER-READABLE STORAGE MEDIUM 有权
标题翻译：图像处理设备，图像处理方法和计算机可读存储介质
公开(公告)号：US20120082341A1
公开(公告)日：2012-04-05
申请号：US13246159
申请日：2011-09-27
申请人： Yuichiro TAKEUCHI
发明人： Yuichiro TAKEUCHI
IPC分类号： G06K9/00
CPC分类号： G09B29/106 , G06T7/0046 , G06T7/75 , G06T13/20 , G06T17/05 , G06T19/006 , G06T19/20 , G06T2200/08 , G06T2215/12 , G06T2215/16 , G06T2219/2016 , G09B29/102 , G09B29/12
摘要： A method is provided for displaying physical objects. The method comprises capturing an input image of physical objects, and matching a three-dimensional model to the physical objects. The method further comprises producing a modified partial image by at least one of modifying a portion of the matched three-dimensional model, or modifying a partial image extracted from the input image using the matched three-dimensional model. The method also comprises displaying an output image including the modified partial image superimposed over the input image.
摘要翻译：提供了一种用于显示物理对象的方法。该方法包括捕获物理对象的输入图像，并将三维模型与物理对象相匹配。该方法还包括通过使用匹配的三维模型修改匹配的三维模型的一部分或修改从输入图像提取的部分图像中的至少一个来产生修改的部分图像。该方法还包括显示包括叠加在输入图像上的经修改的部分图像的输出图像。

9. 发明授权

US06118893A Analysis of an image of a pattern of discrete objects 失效
标题翻译：分析离散对象图案的图像
公开(公告)号：US06118893A
公开(公告)日：2000-09-12
申请号：US895052
申请日：1997-07-16
申请人： David Li
发明人： David Li
IPC分类号： G06T7/00 , G06K9/52 , G06T3/00
CPC分类号： G06T7/0006 , G06T7/0046 , G06T2207/30148 , G06T2207/30152
摘要： An image of an actual pattern of discrete objects is analyzed with respect to a model representing a predefined ideal pattern of objects. Initial processing is performed on only a portion of the image associated with ones of the objects located in an original neighborhood within the image to determine information about an affine transformation of the actual pattern of the discrete objects relative to the predefined ideal pattern. Additional processing is performed on other portions of the image based on the results of the initial processing. Initial processing is performed with respect to a first part of the image by operating on only a first portion of all of the digital data that represents that first part of the image. Later additional processing is performed with respect to another part of the image by operating on only a second portion of all of the digital data that represents that other part of the image, the second portion being relatively smaller than the first portion so that the additional processing is less intensive than the initial processing.
摘要翻译：对于表示预定理想的对象图案的模型，分析离散对象的实际图案的图像。仅对与位于图像内的原始邻域中的对象相关联的图像的一部分执行初始处理，以确定关于相对于预定理想图案的离散对象的实际图案的仿射变换的信息。基于初始处理的结果对图像的其他部分执行附加处理。通过仅对表示图像的第一部分的所有数字数据的第一部分进行操作，对图像的第一部分执行初始处理。稍后通过仅对表示图像的其他部分的所有数字数据的第二部分进行操作来执行关于图像的另一部分的附加处理，第二部分相对小于第一部分，使得附加处理比起初处理要少得多。

10. 发明授权

US5887083A Method of processing image information based on object model 失效
标题翻译：基于对象模型处理图像信息的方法
公开(公告)号：US5887083A
公开(公告)日：1999-03-23
申请号：US683710
申请日：1996-07-18
申请人： Yasushi Sumi , Fumiaki Tomita , Yutaka Ishiyama
发明人： Yasushi Sumi , Fumiaki Tomita , Yutaka Ishiyama
IPC分类号： H04N7/18 , G06K9/64 , G06T1/00 , G06T7/00 , G06T7/60 , H04N13/00 , G06K9/00 , G06K9/48 , G06T17/10
CPC分类号： G06T7/0046 , G06K9/6204 , G06T7/0075 , G06T2207/10012 , H04N13/0055 , H04N13/0059 , H04N13/0239 , H04N2013/0081 , H04N2013/0092
摘要： A method of processing image information is disclosed, for recognizing the position and attitude of an object with a high speed treatment and improved recognition accuracy. The method comprised of the steps of entry of a stereoscopic image of an object, extraction of edges of the object, and dividing it into segments based on the local feature of the image, adding the apex information to the segments to produce the recognition data, verifying the recognition data with reference to an object model based on local geometric features to detect a corresponding candidate; finely adjusting each of corresponding candidates based on an entire geometric features; and detecting the position and attitude of the object on the basis of recognition including the initial verification and the fine adjustment.
摘要翻译：公开了一种处理图像信息的方法，用于以高速处理识别对象的位置和姿态并提高识别精度。该方法包括步骤：输入对象的立体图像，提取对象的边缘，并根据图像的局部特征将其划分成多个段，将顶点信息添加到段以产生识别数据，参照基于局部几何特征的对象模型来验证识别数据以检测相应的候选者; 基于整个几何特征精细调整每个相应的候选者; 并且基于包括初始验证和微调的识别来检测对象的位置和姿态。

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