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

US08896665B2 Camera calibration method and medium and 3D object reconstruction method and medium using the same 有权
标题翻译：相机校准方法和中和3D对象重建方法和介质使用相同
公开(公告)号：US08896665B2
公开(公告)日：2014-11-25
申请号：US11723532
申请日：2007-03-20
申请人： Keun-ho Kim , Seok-yoon Jung , Shin-jun Lee , Gyeong-ja Jang , Vladimir Vezhnevets , Anton Konouchine
发明人： Keun-ho Kim , Seok-yoon Jung , Shin-jun Lee , Gyeong-ja Jang , Vladimir Vezhnevets , Anton Konouchine
IPC分类号： H04N13/02 , G06K9/00 , G06K9/62
CPC分类号： G06T7/80
摘要： A camera calibration method and medium and a 3-dimensional (3D) object reconstruction method and medium using the camera calibration method are provided. The camera calibration method includes setting a feature track by tracking and matching features in an input image sequence; estimating 3-dimensional (3D) points in relation to the features by initializing a structure and motion of the camera; estimating a pose of the camera by using the 3D points and refining the structure of the camera based on the estimated pose; and refining the pose of the camera.
摘要翻译：提供了一种使用相机校准方法的相机校准方法和中等和三维（3D）物体重建方法和介质。相机校准方法包括通过跟踪和匹配输入图像序列中的特征来设置特征轨迹; 通过初始化相机的结构和运动来估计与特征相关的三维（3D）点; 通过使用3D点估计相机的姿态并且基于估计的姿态来改善相机的结构; 并改善相机的姿态。

2. 发明授权

US08254667B2 Method, medium, and system implementing 3D model generation based on 2D photographic images 有权
标题翻译：基于2D摄影图像的方法，媒介和系统实现3D模型生成
公开(公告)号：US08254667B2
公开(公告)日：2012-08-28
申请号：US12068123
申请日：2008-02-01
申请人： Keun-ho Kim , Hui Zhang , Do-kyoon Kim , Seok-yoon Jung , Anton Konouchine , Vladimir Vezhnevets
发明人： Keun-ho Kim , Hui Zhang , Do-kyoon Kim , Seok-yoon Jung , Anton Konouchine , Vladimir Vezhnevets
IPC分类号： G06K9/00 , G06T17/00
CPC分类号： G06T7/536
摘要： A modeling method, medium, and system. The modeling method identifies a object within an image by detecting edges within the image, determines a complexity of the identified object based upon detected surface orientations of the identified object relative to a defined surface of the image, selectively, based upon the determined complexity, generates one or more surfaces for a 3D model by identifying one or more vanishing points for one or more corresponding surfaces, respectively, of the identified object and respectively analyzing the identified one or more vanishing points relative to respective determined points of the one or more corresponding surfaces of the image, and generates the 3D model by combining the one or more surfaces in a 3D space.
摘要翻译：建模方法，介质和系统。建模方法通过检测图像内的边缘来识别图像内的对象，基于所确定的复杂度，基于所确定的对象相对于图像的限定表面的被检测的表面取向来确定所识别的对象的复杂度，从而生成通过分别识别所识别的对象的一个或多个对应表面的一个或多个消失点并相对于所述一个或多个对应表面中的各自确定的点分别分析所识别的一个或多个消失点，用于3D模型的一个或多个表面的图像，并且通过组合3D空间中的一个或多个表面来生成3D模型。

3. 发明申请

US20080211809A1 Method, medium, and system with 3 dimensional object modeling using multiple view points 有权
标题翻译：方法，中等和系统三维对象建模使用多个视点
公开(公告)号：US20080211809A1
公开(公告)日：2008-09-04
申请号：US12010440
申请日：2008-01-24
申请人： Keun-ho Kim , Hui Zhang , Do-kyoon Kim , Seok-yoon Jung , Anton Konouchine , Vladimir Vezhnevets
发明人： Keun-ho Kim , Hui Zhang , Do-kyoon Kim , Seok-yoon Jung , Anton Konouchine , Vladimir Vezhnevets
IPC分类号： G06T17/00
CPC分类号： G06K9/00697 , G06K9/00704 , G06T17/00 , G06T2200/08
摘要： A modeling method, medium, and system. The modeling method may include specifying an object in a plurality of 2 dimensional (2D) images expressed from different view points, considering an edge and contents of each component of each 2D image, generating a 3 dimensional (3D) model of each specified object, and matching the generated 3D models considering relative locations of each generated 3D model. Accordingly, a realistic 3D model of an object expressed in an image can be accurately generated.
摘要翻译：建模方法，介质和系统。该建模方法可以包括在考虑每个2D图像的每个分量的边缘和内容，生成每个指定对象的3维（3D）模型的情况下，在从不同视点表达的多个2维（2D）图像中指定对象，并且考虑所生成的3D模型的相对位置来匹配生成的3D模型。因此，可以精确地生成在图像中表达的对象的逼真的3D模型。

4. 发明授权

US08189031B2 Method and apparatus for providing panoramic view with high speed image matching and mild mixed color blending 有权
标题翻译：用于提供高速图像匹配和温和混合色彩混合的全景视图的方法和装置
公开(公告)号：US08189031B2
公开(公告)日：2012-05-29
申请号：US11591461
申请日：2006-11-02
申请人： Keun Ho Kim , Do Kyoon Kim , Seok Yoon Jung , Hee Sae Lee , Anton Konouchine , Vladimir Vezhnevets
发明人： Keun Ho Kim , Do Kyoon Kim , Seok Yoon Jung , Hee Sae Lee , Anton Konouchine , Vladimir Vezhnevets
IPC分类号： H04N7/00
CPC分类号： G06T3/4038
摘要： An apparatus and method of providing a panoramic image, the method including: preparing images of a plurality of levels, which are made by scaling each of two source images at several rates; computing a Sum of Square Difference (SSD) between two corresponding images in each of the plurality of levels of the two source images to form an image stitched together; and when stitching the two images, the overlapping area is divided into a plurality of parts and each part is assigned a weight which is linearly applied respectively to the divided part of each source image for blending color. The apparatus includes stitching units to stitch source images together at the plurality of levels and blending units to color blend the source images in the overlapped area.
摘要翻译：一种提供全景图像的装置和方法，所述方法包括：通过以几个比例缩放两个源图像中的每一个来制作多个级别的图像; 计算两个源图像的多个级别中的每一个中的两个对应图像之间的平方差（SSD）的和，以形成拼接在一起的图像; 并且当拼接两个图像时，重叠区域被分成多个部分，并且每个部分被分配一个分别线性地施加到每个源图像的分割部分以用于混合颜色的权重。该装置包括缝合单元，以在多个级别上将源图像拼接在一起，并且混合单元将颜色混合在重叠区域中的源图像。

5. 发明申请

US20080208547A1 Method, medium, and system implementing 3D model generation based on 2D photographic images 有权
标题翻译：基于2D摄影图像的方法，媒介和系统实现3D模型生成
公开(公告)号：US20080208547A1
公开(公告)日：2008-08-28
申请号：US12068123
申请日：2008-02-01
申请人： Keun-ho Kim , Hui Zhang , Do-kyoon Kim , Seok-yoon Jung , Anton Konouchine , Vladimir Vezhnevets
发明人： Keun-ho Kim , Hui Zhang , Do-kyoon Kim , Seok-yoon Jung , Anton Konouchine , Vladimir Vezhnevets
IPC分类号： G06F17/00
CPC分类号： G06T7/536
摘要： A modeling method, medium, and system. The modeling method identifies a object within an image by detecting edges within the image, determines a complexity of the identified object based upon detected surface orientations of the identified object relative to a defined surface of the image, selectively, based upon the determined complexity, generates one or more surfaces for a 3D model by identifying one or more vanishing points for one or more corresponding surfaces, respectively, of the identified object and respectively analyzing the identified one or more vanishing points relative to respective determined points of the one or more corresponding surfaces of the image, and generates the 3D model by combining the one or more surfaces in a 3D space.
摘要翻译：建模方法，介质和系统。建模方法通过检测图像内的边缘来识别图像内的对象，基于所确定的复杂度，基于所确定的对象相对于图像的限定表面的被检测的表面取向来确定所识别的对象的复杂度，从而生成通过分别识别所识别的对象的一个或多个对应表面的一个或多个消失点并相对于所述一个或多个对应表面中的各自确定的点分别分析所识别的一个或多个消失点，用于3D模型的一个或多个表面的图像，并且通过组合3D空间中的一个或多个表面来生成3D模型。

6. 发明申请

US20070253618A1 Camera calibration method and medium and 3D object reconstruction method and medium using the same 有权
标题翻译：相机校准方法和中和3D对象重建方法和介质使用相同
公开(公告)号：US20070253618A1
公开(公告)日：2007-11-01
申请号：US11723532
申请日：2007-03-20
申请人： Keun-ho Kim , Seok-yoon Jung , Shin-jun Lee , Gyeong-ja Jang , Vladimir Vezhnevets , Anton Konouchine
发明人： Keun-ho Kim , Seok-yoon Jung , Shin-jun Lee , Gyeong-ja Jang , Vladimir Vezhnevets , Anton Konouchine
IPC分类号： G06T17/20
CPC分类号： G06T7/80
摘要： A camera calibration method and medium and a 3-dimensional (3D) object reconstruction method and medium using the camera calibration method are provided. The camera calibration method includes setting a feature track by tracking and matching features in an input image sequence; estimating 3-dimensional (3D) points in relation to the features by initializing a structure and motion of the camera; estimating a pose of the camera by using the 3D points and refining the structure of the camera based on the estimated pose; and refining the pose of the camera.
摘要翻译：提供了一种使用相机校准方法的相机校准方法和中等和三维（3D）物体重建方法和介质。相机校准方法包括通过跟踪和匹配输入图像序列中的特征来设置特征轨迹; 通过初始化相机的结构和运动来估计与特征相关的三维（3D）点; 通过使用3D点估计相机的姿态并且基于估计的姿态来改善相机的结构; 并改善相机的姿态。

7. 发明申请

US20050063582A1 Method and apparatus for image-based photorealistic 3D face modeling 有权
标题翻译：用于基于图像的逼真3D脸部建模的方法和装置
公开(公告)号：US20050063582A1
公开(公告)日：2005-03-24
申请号：US10927241
申请日：2004-08-27
申请人： In-Kyu Park , Heui-Keun Choh , Vladimir Vezhnevets , Hui Zhang
发明人： In-Kyu Park , Heui-Keun Choh , Vladimir Vezhnevets , Hui Zhang
IPC分类号： G06K9/00 , G06K9/62 , G06T7/00 , G06T17/10
CPC分类号： G06T17/10
摘要： An apparatus and method for image-based 3D photorealistic head modeling are provided. The method for creating a 3D photorealistic head model includes: detecting frontal and profile features in input frontal and profile images; generating a 3D head model by fitting a 3D genetic model using the detected facial features; generating a realistic texture from the input frontal and profile images; and mapping the texture onto the 3D head model. In the apparatus and method, data obtained using a relatively cheap device, such as a digital camera, can be processed in an automated manner, and satisfactory results can be obtained even from imperfect input data. In other words, facial features can be extracted in an automated manner, and a robust “human-quality” face analysis algorithm is used.
摘要翻译：提供了一种用于基于图像的3D照片写实头部建模的装置和方法。创建3D逼真头模型的方法包括：检测输入正面和轮廓图像中的正面和轮廓特征; 通过使用检测到的面部特征拟合3D遗传模型来生成3D头部模型; 从输入正面和轮廓图像生成逼真的纹理; 并将纹理映射到3D头模型上。在该装置和方法中，可以使用诸如数码相机的相对便宜的装置获得的数据以自动方式进行处理，并且甚至可以从不完美的输入数据获得令人满意的结果。换句话说，可以以自动的方式提取面部特征，并且使用健壮的“人质”面部分析算法。

8. 发明授权

US08681150B2 Method, medium, and system with 3 dimensional object modeling using multiple view points 有权
标题翻译：方法，中等和系统三维对象建模使用多个视点
公开(公告)号：US08681150B2
公开(公告)日：2014-03-25
申请号：US12010440
申请日：2008-01-24
申请人： Keun-ho Kim , Hui Zhang , Do-kyoon Kim , Seok-yoon Jung , Anton Konouchine , Vladimir Vezhnevets
发明人： Keun-ho Kim , Hui Zhang , Do-kyoon Kim , Seok-yoon Jung , Anton Konouchine , Vladimir Vezhnevets
IPC分类号： G06T17/00
CPC分类号： G06K9/00697 , G06K9/00704 , G06T17/00 , G06T2200/08
摘要： A modeling method, medium, and system. The modeling method may include specifying an object in a plurality of 2 dimensional (2D) images expressed from different view points, considering an edge and contents of each component of each 2D image, generating a 3 dimensional (3D) model of each specified object, and matching the generated 3D models considering relative locations of each generated 3D model. Accordingly, a realistic 3D model of an object expressed in an image can be accurately generated.
摘要翻译：建模方法，介质和系统。该建模方法可以包括在考虑每个2D图像的每个分量的边缘和内容，生成每个指定对象的3维（3D）模型的情况下，在从不同视点表达的多个2维（2D）图像中指定对象，并且考虑所生成的3D模型的相对位置来匹配生成的3D模型。因此，可以精确地生成在图像中表达的对象的逼真的3D模型。

9. 发明授权

US07899270B2 Method and apparatus for providing panoramic view with geometric correction 有权
标题翻译：用于提供具有几何校正的全景图的方法和装置
公开(公告)号：US07899270B2
公开(公告)日：2011-03-01
申请号：US11581401
申请日：2006-10-17
申请人： Keun Ho Kim , Do Kyoon Kim , Seok Yoon Jung , Hee Sae Lee , Anton Konouchine , Vladimir Vezhnevets
发明人： Keun Ho Kim , Do Kyoon Kim , Seok Yoon Jung , Hee Sae Lee , Anton Konouchine , Vladimir Vezhnevets
IPC分类号： G06K9/36 , G06K9/32 , H04N3/36
CPC分类号： H04N5/2628 , G06T3/4038 , G06T5/006 , H04N5/23238
摘要： A method and apparatus of correcting geometric information and providing a panoramic view. In the method of providing a panoramic view, a tilting vector (X′, Y′) is generated by applying matrices H(a,b) and HF to a source image vector (X,Y). The matrix H(a,b) is defined by distortion angles “b” towards a plane direction and a distortion angle “a” towards a depth direction of the source image, and the matrix HF is defined according to a camera parameter matrix K. Also, a two-dimensional vector (x,y) of a source image is converted into a three-dimensional vector (X,Y,W) on a retinal image plane having a unit radial distance from an origin of a ground plane. Also, a warped image width (WIW) is estimated from a width and a field of view (FOV) of the source image. A warping vector (x′,y′) is generated based on the converted vector (X,Y,W) and the WIW.
摘要翻译：一种校正几何信息并提供全景的方法和装置。在提供全景图的方法中，通过将矩阵H（a，b）和HF应用于源图像矢量（X，Y）来产生倾斜矢量（X'，Y'）。矩阵H（a，b）由朝向平面方向的畸变角“b”和朝向源图像的深度方向的畸变角“a”定义，矩阵HF根据照相机参数矩阵K来定义。此外，源图像的二维向量（x，y）在具有距接地平面的原点的单位径向距离的视网膜图像平面上被转换为三维矢量（X，Y，W）。此外，从源图像的宽度和视场（FOV）估计翘曲图像宽度（WIW）。基于转换的矢量（X，Y，W）和WIW产生翘曲矢量（x'，y'）。

10. 发明授权

US07835568B2 Method and apparatus for image-based photorealistic 3D face modeling 有权
标题翻译：用于基于图像的逼真3D脸部建模的方法和装置
公开(公告)号：US07835568B2
公开(公告)日：2010-11-16
申请号：US10927241
申请日：2004-08-27
申请人： In-Kyu Park , Heui-Keun Choh , Vladimir Vezhnevets , Hui Zhang
发明人： In-Kyu Park , Heui-Keun Choh , Vladimir Vezhnevets , Hui Zhang
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06T17/10
摘要： An apparatus and method for image-based 3D photorealistic head modeling are provided. The method for creating a 3D photorealistic head model includes: detecting frontal and profile features in input frontal and profile images; generating a 3D head model by fitting a 3D genetic model using the detected facial features; generating a realistic texture from the input frontal and profile images; and mapping the texture onto the 3D head model. In the apparatus and method, data obtained using a relatively cheap device, such as a digital camera, can be processed in an automated manner, and satisfactory results can be obtained even from imperfect input data. In other words, facial features can be extracted in an automated manner, and a robust “human-quality” face analysis algorithm is used.
摘要翻译：提供了一种用于基于图像的3D照片写实头部建模的装置和方法。创建3D逼真头模型的方法包括：检测输入正面和轮廓图像中的正面和轮廓特征; 通过使用检测到的面部特征拟合3D遗传模型来生成3D头部模型; 从输入正面和轮廓图像生成逼真的纹理; 并将纹理映射到3D头模型上。在该装置和方法中，可以使用诸如数码相机的相对便宜的装置获得的数据以自动方式进行处理，并且甚至可以从不完美的输入数据获得令人满意的结果。换句话说，可以以自动的方式提取面部特征，并且使用健壮的“人质”面部分析算法。

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