专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明授权

US08600106B1 Method and apparatus for tracking objects within a video frame sequence 有权
标题翻译：用于跟踪视频帧序列内的对象的方法和装置
公开(公告)号：US08600106B1
公开(公告)日：2013-12-03
申请号：US12807236
申请日：2010-08-31
申请人： Alexandre Parenteau , Abhinav Darbari , Timothy H. Roth , Manish S. Kulkarni , Hailin Jin
发明人： Alexandre Parenteau , Abhinav Darbari , Timothy H. Roth , Manish S. Kulkarni , Hailin Jin
IPC分类号： G06K9/00
CPC分类号： G06K9/00261 , G06T7/246 , G06T2207/20016 , G06T2207/30201 , G06T2207/30241
摘要： A method and apparatus for tracking objects within a video frame sequence. In one embodiment, a method for tracking an object within a video frame sequence is disclosed. The method includes processing each jth frame of the video frame sequence to determine a motion vector defining motion between a prior jth frame and a current jth frame. The method includes creating an object descriptor for an object being tracked followed by generating a document object model comprising motion information and the object descriptor.
摘要翻译：一种用于跟踪视频帧序列内的对象的方法和装置。在一个实施例中，公开了一种用于跟踪视频帧序列内的对象的方法。该方法包括处理视频帧序列的每个第j帧以确定定义在第j个帧和第j个帧之间运动的运动矢量。该方法包括为被跟踪的对象创建对象描述符，随后生成包含运动信息和对象描述符的文档对象模型。

32. 发明申请

US20130120375A1 SELECTIVELY DISPLAYING SURFACES OF AN OBJECT MODEL 有权
标题翻译：选择对象模型的显示表面
公开(公告)号：US20130120375A1
公开(公告)日：2013-05-16
申请号：US12323242
申请日：2008-11-25
申请人： Hailin Jin , Liang Wang
发明人： Hailin Jin , Liang Wang
IPC分类号： G06T17/00
CPC分类号： G06T19/00 , G06T2210/36
摘要： Techniques for selectively displaying surfaces of an object model to a user are described. In one embodiment, a computer-implemented method may include, for a given one of a plurality of surfaces included in an object model that is representative of a physical object, determining a normal vector of the given surface. The method may also include determining an angle between the normal vector of the given surface and a current viewing direction of the model. The method may further include displaying the object model to a user without displaying the given surface to the user, dependent upon determining that the angle between the normal vector and the current viewing direction is greater than a threshold value.
摘要翻译：描述用于向用户选择性地显示对象模型的表面的技术。在一个实施例中，对于包括在代表物理对象的对象模型中的多个表面中的给定的一个表面，计算机实现的方法可以包括确定给定表面的法向向量。该方法还可以包括确定给定表面的法向量与模型的当前观察方向之间的角度。该方法还可以包括：根据确定法向量与当前观察方向之间的角度大于阈值，将对象模型显示给用户而不向用户显示给定的表面。

33. 发明授权

US08270770B1 Region-based dense feature correspondence 有权
标题翻译：基于区域的密集特征函数
公开(公告)号：US08270770B1
公开(公告)日：2012-09-18
申请号：US12323089
申请日：2008-11-25
申请人： Hailin Jin , Kai Ni
发明人： Hailin Jin , Kai Ni
IPC分类号： G06K9/32 , G06K9/36
CPC分类号： G06T7/11 , G06T7/579 , G06T2207/10024 , G06T2207/30244
摘要： In one embodiment, a method comprises determining an initial set of feature correspondences for a pair of images of a three dimensional (3D) space; identifying one or more first regions in one of the pair of images and one or more second regions in the other one of the pair of images. The method comprises identifying additional feature correspondences by matching first regions and second regions in the pair of images and generating a motion of a camera in the 3D space responsive to the initial set of feature correspondences and the additional feature correspondences, wherein the camera captured the images. Each of the first regions and the second regions potentially maps to a plane in the 3D space corresponding to the images. Additionally, each of the first regions and the second regions includes at least one feature in the initial set of feature correspondences.
摘要翻译：在一个实施例中，一种方法包括确定三维（3D）空间的一对图像的特征对应的初始集合; 识别所述一对图像之一中的一个或多个第一区域以及所述一对图像中的另一个中的一个或多个第二区域。该方法包括通过匹配该对图像中的第一区域和第二区域来识别附加特征对应，并且响应于初始的特征对应和附加特征对应而在3D空间中产生照相机的运动，其中相机捕获图像。第一区域和第二区域中的每一个可能映射到与图像对应的3D空间中的平面。另外，第一区域和第二区域中的每一个包括初始特征对应集合中的至少一个特征。

34. 发明授权

US08265422B1 Method and apparatus for removing general lens distortion from images 有权
标题翻译：用于从图像中去除一般透镜失真的方法和装置
公开(公告)号：US08265422B1
公开(公告)日：2012-09-11
申请号：US12390317
申请日：2009-02-20
申请人： Hailin Jin
发明人： Hailin Jin
IPC分类号： G06K9/40 , H04N9/74
CPC分类号： H04N5/3572 , G06T3/0093 , G06T5/006
摘要： Method and apparatus for removing general geometric lens distortion from images. A geometric distortion removal algorithm is implemented according to a general 5-parameter distortion model that includes both radial and tangential lens distortion components. The algorithm may be implemented in a two-stage process in which one-dimensional elements in one planar dimension (rows or columns) of an input image with geometric distortion are rendered to generate an intermediate buffer, and then one-dimensional elements in the other planar dimension (columns or rows) of the intermediate buffer are rendered to generate an output image with geometric distortion reduced or removed. Thus, one-dimensional sampling is performed, and interpolation is performed in one planar dimension, rather than 2-D interpolation. An input row or column may be decimated, if necessary, before row or column interpolation is performed to generate an output row or column. Since decimation is performed in one dimension, aliasing artifacts may be prevented.
摘要翻译：从图像中去除一般几何透镜失真的方法和装置。根据包括径向和切向透镜失真分量的通用5参数失真模型来实现几何失真去除算法。该算法可以在二阶段过程中实现，其中渲染具有几何失真的输入图像的一个平面维度（行或列）中的一维元素以生成中间缓冲器，然后在另一个过程中的一维元素渲染中间缓冲器的平面尺寸（列或行）以产生几何失真减少或去除的输出图像。因此，进行一维采样，并且在一个平面维度上进行插值，而不是2-D插值。如果需要，在执行行或列插值以生成输出行或列之前，可以抽取输入行或列。由于在一个维度上执行抽取，可以防止混叠伪像。

35. 发明授权

US08217956B1 Method and apparatus for rendering spherical panoramas 有权
标题翻译：渲染球形全景的方法和装置
公开(公告)号：US08217956B1
公开(公告)日：2012-07-10
申请号：US12040504
申请日：2008-02-29
申请人： Hailin Jin
发明人： Hailin Jin
IPC分类号： G09G5/00
CPC分类号： G06T15/10 , G06T3/60 , G06T15/04
摘要： Method and apparatus for rendering panoramas under spherical projections. A set of component images and alignment parameters for the images are obtained. A rotation matrix for a component image is decomposed into three rotation matrices. An in-plane rotation of the image is performed to generate a rotated image. Once an in-plane rotation is performed, the rotated image is rendered first in one planar (x or y) dimension (whether columns or rows) to generate an intermediate image, and then the intermediate image is rendered in the other planar dimension to generate an output image. Decimation of the input rows and columns may be performed if necessary, and one-dimensional interpolation may be performed to generate pixel values in the output rows and columns from pixel values in the input rows and columns. The output image may be adjusted on the spherical projection by shifting the bounding box of the output image.
摘要翻译：在全球投影下呈现全景的方法和装置。获得图像的一组分量图像和对准参数。用于分量图像的旋转矩阵被分解成三个旋转矩阵。执行图像的平面内旋转以产生旋转的图像。一旦执行平面内旋转，旋转的图像首先被渲染在一个平面（x或y）维度（无论是列或行）中以生成中间图像，然后中间图像在另一个平面维度上呈现，以产生输出图像。如果需要，可以执行输入行和列的抽取，并且可以执行一维内插以从输入行和列中的像素值生成输出行和列中的像素值。通过移动输出图像的边界框，可以在球面投影上调整输出图像。

36. 发明授权

US08131113B1 Method and apparatus for estimating rotation, focal lengths and radial distortion in panoramic image stitching 有权
标题翻译：用于估算全景图像拼接中的旋转，焦距和径向失真的方法和装置
公开(公告)号：US08131113B1
公开(公告)日：2012-03-06
申请号：US12035954
申请日：2008-02-22
申请人： Hailin Jin
发明人： Hailin Jin
IPC分类号： G06K9/32 , H04N7/00 , G09G5/00
CPC分类号： G06T7/74 , G06T7/337 , G06T2207/30244
摘要： Method and apparatus for estimating relative three-dimensional (3D) camera rotations, focal lengths, and radial (lens) distortions from point-correspondences in pairwise (two image) image alignment. A core estimator takes a minimal (three) number of point-correspondences and returns a rotation, lens (radial) distortion and two focal lengths. The core estimator solves relative 3D camera rotations, and lens distortions from 3-point-correspondences in two images in the presence of noise in point-correspondences. A robust estimator may be based on or may be “wrapped around” the core estimator to handle noise and errors in point-correspondences. The robust estimator may determine an alignment model for a pair of images from the rotation, distortion, and focal lengths.
摘要翻译：用于从成对（两个图像）图像对准中的点对应估计相对三维（3D）相机旋转，焦距和径向（透镜）失真的方法和装置。核心估计器采用最小（三）个点对应，并返回旋转，透镜（径向）失真和两个焦距。核心估计器解决相对3D摄像机旋转，以及在存在噪声的情况下在两个图像中的3点对应的透镜失真。鲁棒的估计器可以基于或可以“缠绕”核心估计器以处理点对应的噪声和误差。鲁棒估计器可以根据旋转，失真和焦距确定一对图像的对准模型。

37. 发明授权

US08063918B2 Method and apparatus for rendering images with and without radially symmetric distortions 有权
标题翻译：用于渲染具有和不具有径向对称失真的图像的方法和装置
公开(公告)号：US08063918B2
公开(公告)日：2011-11-22
申请号：US12128164
申请日：2008-05-28
申请人： Hailin Jin
发明人： Hailin Jin
IPC分类号： G09G5/00
CPC分类号： G06T5/006 , G06T3/0018
摘要： A method and apparatus for rendering images with and without radially symmetric distortions is described in which the forward and backward radial distortion rendering processes are decomposed into two stages. One-dimensional elements in one planar dimension (rows or columns) of an input image are rendered to generate an intermediate buffer, and then one-dimensional elements in the other planar dimension (columns or rows) of the intermediate buffer are rendered to generate an output image. Thus, one-dimensional sampling is performed, and interpolation may be performed in one planar dimension, rather than 2-D interpolation. An input row or column may be decimated, if necessary, before row or column interpolation is performed to generate an output row or column.
摘要翻译：描述用于渲染具有和不具有径向对称失真的图像的方法和装置，其中向前和向后的径向失真渲染处理被分解成两个阶段。渲染输入图像的一个平面尺寸（行或列）中的一维元素以生成中间缓冲器，然后呈现中间缓冲器的另一个平面维（列或行）中的一维元素，以生成输出图像。因此，执行一维采样，并且可以在一个平面维度中进行插值，而不是2-D插值。如果需要，在执行行或列插值以生成输出行或列之前，可以抽取输入行或列。

38. 发明申请

US20100053347A1 Content-Aware Video Stabilization 有权
标题翻译：内容感知视频稳定
公开(公告)号：US20100053347A1
公开(公告)日：2010-03-04
申请号：US12276119
申请日：2008-11-21
申请人： Aseem O. Agarwala , Feng Liu , Hailin Jin
发明人： Aseem O. Agarwala , Feng Liu , Hailin Jin
IPC分类号： H04N5/228
CPC分类号： H04N5/23248 , H04N5/23267
摘要： In one embodiment, a method comprises receiving a source video sequence; determining a stabilized camera path to which the source video sequence is to be stabilized; and generating a stabilized video sequence, wherein each frame of the stabilized video sequence is generated as a content-aware warp of a corresponding frame in the input sequence.
摘要翻译：在一个实施例中，一种方法包括接收源视频序列; 确定源视频序列将被稳定的稳定的相机路径; 以及生成稳定视频序列，其中，所述稳定视频序列的每个帧被生成为所述输入序列中对应帧的内容感知扭曲。

39. 发明授权

US09202278B2 Plane-based self-calibration for structure from motion 有权
标题翻译：基于平面的自校准结构从运动
公开(公告)号：US09202278B2
公开(公告)日：2015-12-01
申请号：US13551601
申请日：2012-07-17
申请人： Hailin Jin , Zihan Zhou
发明人： Hailin Jin , Zihan Zhou
IPC分类号： G06K9/00 , G06T7/00 , G06T7/20
CPC分类号： G06T7/80 , G06T7/174 , G06T7/20 , G06T2207/10016 , G06T2207/30241 , H04N13/20
摘要： Robust techniques for self-calibration of a moving camera observing a planar scene. Plane-based self-calibration techniques may take as input the homographies between images estimated from point correspondences and provide an estimate of the focal lengths of all the cameras. A plane-based self-calibration technique may be based on the enumeration of the inherently bounded space of the focal lengths. Each sample of the search space defines a plane in the 3D space and in turn produces a tentative Euclidean reconstruction of all the cameras that is then scored. The sample with the best score is chosen and the final focal lengths and camera motions are computed. Variations on this technique handle both constant focal length cases and varying focal length cases.
摘要翻译：用于自动校准移动摄像机观察平面场景的强大技术。基于平面的自校准技术可以将从点对应估计的图像之间的同形作为输入，并提供所有相机的焦距的估计。基于平面的自校准技术可以基于焦距的固有界限空间的计数。搜索空间的每个样本在3D空间中定义一个平面，并且反过来产生所有相机的临时欧几里德重建，然后对其进行评分。选择具有最佳分数的样本，并计算最终焦距和相机运动。该技术的变化处理恒定焦距情况和不同焦距情况。

40. 发明申请

US20130129191A1 Methods and Apparatus for Image Rectification for Stereo Display 有权
标题翻译：用于立体显示的图像校正的方法和装置
公开(公告)号：US20130129191A1
公开(公告)日：2013-05-23
申请号：US12954135
申请日：2010-11-24
申请人： Hailin Jin , Jialue Fan
发明人： Hailin Jin , Jialue Fan
IPC分类号： G06K9/00
CPC分类号： G06T7/33 , G06T7/85 , G06T2207/10004 , G06T2207/10012 , G06T2207/20021 , H04N13/122 , H04N13/133 , H04N2013/0074
摘要： A set of features in a pair of images is associated to selected cells within a set of cells using a base mesh. Each image of the pair of images is divided using the base mesh to generate the set of cells. The set of features is defined in terms of the selected cells. A stereo image pair is generated by transforming the set of cells with a mesh-based transformation function. A transformation of the set of cells is computed by applying an energy minimization function to the set of cells. A selected transformed mesh and another transformed mesh are generated by applying the transformation of the set of cells to the base mesh. The mesh-based transformation function preserves selected properties of the set of features in the pair of images.
摘要翻译：一对图像中的一组特征与使用基本网格的一组单元格内的所选单元相关联。使用基本网格划分一对图像的每个图像以生成单元格集合。特征集是根据选定的单元格来定义的。通过用基于网格的变换函数变换单元格集来生成立体图像对。通过将能量最小化函数应用于该组单元来计算该组单元的变换。通过将该组细胞的变换应用于基本网格来生成选择的变换网格和另一变换的网格。基于网格的变换函数保留了该对图像中特征集的选定属性。

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