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

US10097813B2 Methods and systems for capturing 3D surface geometry 有权
公开(公告)号：US10097813B2
公开(公告)日：2018-10-09
申请号：US13408488
申请日：2012-02-29
申请人： Bjorn Stenger , Atsuto Maki , Frank Perbet , Oliver Woodford , Roberto Cipolla , Robert Anderson
发明人： Bjorn Stenger , Atsuto Maki , Frank Perbet , Oliver Woodford , Roberto Cipolla , Robert Anderson
IPC分类号： H04N13/25 , H04N13/128 , H04N13/122 , H04N13/271 , H04N13/254 , G06T7/593 , H04N13/125 , H04N13/268
摘要： A system for capturing 3D image data of a scene, including three light sources, each configured to emit light at a different wavelength to the other two sources and to illuminate the scene to be captured; a first video camera configured to receive light from the light sources which has been reflected from the scene, to isolate light received from each of the light sources, and to output data relating to the image captured for each of the three light sources; a depth sensor configured to capture depth map data of the scene; and an analysis unit configured to receive data from the first video camera and process the data to obtain data relating to a normal field obtained from the images captured for each of the three light sources, and to combine the normal field data with the depth map data to capture 3D image data of the scene.

2. 发明授权

US08849039B2 Image processing method and system 有权
标题翻译：图像处理方法和系统
公开(公告)号：US08849039B2
公开(公告)日：2014-09-30
申请号：US13407357
申请日：2012-02-28
申请人： Minh-Tri Pham , Oliver Woodford , Frank Perbet , Atsuto Maki , Bjorn Stenger , Roberto Cipolla
发明人： Minh-Tri Pham , Oliver Woodford , Frank Perbet , Atsuto Maki , Bjorn Stenger , Roberto Cipolla
IPC分类号： G06K9/48 , G06T7/00 , G06K9/00 , G06K9/20
CPC分类号： G06T7/0042 , G06F17/30259 , G06K9/00214 , G06K9/2036 , G06K9/6202 , G06T3/20 , G06T3/60 , G06T7/586 , G06T7/73 , G06T2207/10024 , G06T2207/30208 , G06T2207/30244
摘要： A method of comparing two object poses, wherein each object pose is expressed in terms of position, orientation and scale with respect to a common coordinate system, the method comprising: calculating a distance between the two object poses, the distance being calculated using the distance function: d sRt ⁡ ( X , Y ) = d s 2 ⁡ ( X , Y ) σ s 2 + d r 2 ⁡ ( X , Y ) σ r 2 + d t 2 ⁡ ( X , Y ) σ t 2 . where X is the object pose of one object and Y is the object pose of the other object, d s ⁡ ( X , Y ) =  log ⁡ ( s ⁡ ( X ) s ⁡ ( Y ) )  , ⁢ d r ⁡ ( X , Y ) =  R ⁡ ( X ) - R ⁡ ( Y )  F , ⁢ d t ⁡ ( X , Y ) =  t ⁡ ( X ) - t ⁡ ( Y )  s ⁡ ( Y ) , s(X) and s(Y) are scalar functions representing the scale of the object poses X and Y respectively, R(X) and R(Y) are matrices expressing the rotation of object poses X and Y respectively, t(X) and t(Y) are vectors expressing the translation of object poses X and Y respectively, and σs, σr and σt are weighting factors for ds, dr and dt respectively.
摘要翻译：一种比较两个物体姿态的方法，其中每个物体姿态相对于公共坐标系以位置，方向和比例表示，所述方法包括：计算两个物体姿势之间的距离，使用距离计算距离函数：d sRt⁡（X，Y）= ds 2⁡（X，Y）＆sgr; s 2 + d r 2⁡（X，Y）＆sgr; r 2 + d t 2⁡（X，Y）＆sgr; t 2。其中X是一个对象的对象姿态，Y是另一个对象的对象姿态，ds⁡（X，Y）= log log（s⁡（X）s⁡（Y））庇，dr⁡（X ，Y）=R⁡（X） - R⁡（Y）F，dt⁡（X，Y）=t⁡（X）-t⁡（Y）s⁡（Y））和s（Y）分别表示对象姿态X和Y的尺度的标量函数，R（X）和R（Y）分别表示对象姿势X和Y的旋转矩阵，t（X）和t（ Y）是分别表示对象姿势X和Y的平移的矢量，＆sgr，s，＆sgr; r和＆sgr; t分别是ds，dr和dt的权重因子。

3. 发明申请

US20130016913A1 IMAGE PROCESSING METHOD AND SYSTEM 有权
标题翻译：图像处理方法和系统
公开(公告)号：US20130016913A1
公开(公告)日：2013-01-17
申请号：US13407357
申请日：2012-02-28
申请人： Minh-Tri Pham , Oliver Woodford , Frank Perbet , Atsuto Maki , Bjorn Stenger , Roberto Cipolla
发明人： Minh-Tri Pham , Oliver Woodford , Frank Perbet , Atsuto Maki , Bjorn Stenger , Roberto Cipolla
IPC分类号： G06K9/68
CPC分类号： G06T7/0042 , G06F17/30259 , G06K9/00214 , G06K9/2036 , G06K9/6202 , G06T3/20 , G06T3/60 , G06T7/586 , G06T7/73 , G06T2207/10024 , G06T2207/30208 , G06T2207/30244
摘要： A method of comparing two object poses, wherein each object pose is expressed in terms of position, orientation and scale with respect to a common coordinate system, the method comprising:calculating a distance between the two object poses, the distance being calculated using the distance function: d sRt  ( X , Y ) = d s 2  ( X , Y ) σ s 2 + d r 2  ( X , Y ) σ r 2 + d t 2  ( X , Y ) σ t 2 . where X is the object pose of one object and Y is the object pose of the other object, d s  ( X , Y ) =  log  ( s  ( X ) s  ( Y ) )  ,  d r  ( X , Y ) =  R  ( X ) - R  ( Y )  F ,  d t  ( X , Y ) =  t  ( X ) - t  ( Y )  s  ( Y ) , s(X) and s(Y) are scalar functions representing the scale of the object poses X and Y respectively, R(X) and R(Y) are matrices expressing the rotation of object poses X and Y respectively, t(X) and t(Y) are vectors expressing the translation of object poses X and Y respectively, and σs, or and σt are weighting factors for ds, dr and dt respectively.
摘要翻译：一种比较两个物体姿态的方法，其中每个物体姿态相对于公共坐标系以位置，方向和比例表示，所述方法包括：计算两个物体姿势之间的距离，使用距离计算距离函数：d sRt（X，Y）= ds 2（X，Y）＆sgr; s 2 + d r 2（X，Y）＆sgr; r 2 + d t 2（X，Y）＆sgr; t 2。其中X是一个对象的对象姿态，Y是另一个对象的对象姿态，其中X（X，Y）=（log）（s（X）s（Y）），dr （Y）（X） - R（Y）F，dt（X，Y）=t（X） - t（Y））和s（Y）分别表示对象姿态X和Y的尺度的标量函数，R（X）和R（Y）分别表示对象姿势X和Y的旋转矩阵，t（X）和t（ Y）是分别表示对象姿势X和Y的平移的矢量，＆sgr，s，和＆sgr; t分别是ds，dr和dt的加权因子。

4. 发明授权

US08750614B2 Method and system for classifying features in a video sequence 失效
标题翻译：用于对视频序列中的特征进行分类的方法和系统
公开(公告)号：US08750614B2
公开(公告)日：2014-06-10
申请号：US13239602
申请日：2011-09-22
申请人： Atsuto Maki , Frank Perbet , Bjorn Stenger , Oliver Woodford , Roberto Cipolla
发明人： Atsuto Maki , Frank Perbet , Bjorn Stenger , Oliver Woodford , Roberto Cipolla
IPC分类号： G06K9/00 , G06K9/62 , G06K9/34
CPC分类号： G06K9/00369 , G06K9/4642
摘要： According to one embodiment, a method of classifying a feature in a video sequence includes selecting a target region of a frame of the video sequence, where the target region contains the feature; dividing the target region into a plurality cells, calculating histograms of optic flow with the cells comparing the histograms of optic flow for pairs of cells; and assigning the feature to a class based at least in part on the result of the comparison.
摘要翻译：根据一个实施例，对视频序列中的特征进行分类的方法包括：选择目标区域包含该特征的视频序列的帧的目标区域; 将目标区域划分成多个单元，计算细胞的直方图，其中细胞比较细胞对的光学流的直方图; 以及至少部分地基于所述比较的结果将所述特征分配给类。

5. 发明授权

US08417021B2 Image processing methods and apparatus 失效
标题翻译：图像处理方法和装置
公开(公告)号：US08417021B2
公开(公告)日：2013-04-09
申请号：US12089140
申请日：2006-10-12
申请人： Roberto Cipolla , George Vogiatzis , Paolo Favaro , Ryuji Funayama , Hiromichi Yanagihara
发明人： Roberto Cipolla , George Vogiatzis , Paolo Favaro , Ryuji Funayama , Hiromichi Yanagihara
IPC分类号： G06K9/00
CPC分类号： G06T7/579 , G06T7/557 , G06T7/586 , G06T2207/10021 , G06T2207/30264
摘要： We describe methods of characterizing a set of images to determine their respective illumination, for example for recovering the 3D shape of an illuminated object. The method comprises: inputting a first set of images of the object captured from different positions; determining frontier point data from the images, this defining a plurality of frontier points on the object and for each said frontier point a direction of a normal to the surface of the object at the frontier point, and determining data defining the image capture positions; inputting a second set of images of said object, having substantially the same viewpoint and different illumination conditions; and characterizing the second set of images said frontier point data to determine data comprising object reflectance parameter data (β) and, for each image of said second set, illumination data (L) comprising data defining an illumination direction and illumination intensity for the image.
摘要翻译：我们描述表征一组图像的方法以确定它们各自的照明，例如用于恢复被照亮物体的3D形状。该方法包括：输入从不同位置捕获的对象的第一组图像; 确定来自图像的边界点数据，其定义对象上的多个边界点，并为每个所述前沿点定义在边界点处的对象的表面的法线方向，以及确定定义图像捕获位置的数据; 输入所述对象的第二组图像，具有基本上相同的视点和不同的照明条件; 并且表征所述第二组图像，所述边界点数据以确定包括对象反射参数数据（＆bgr）的数据，并且对于所述第二组的每个图像，包括限定图像的照明方向和照明强度的数据的照明数据（L）。

6. 发明申请

US20130084008A1 METHODS AND SYSTEMS FOR SEMANTIC LABEL PROPAGATION 有权
标题翻译：语义标签传播的方法与系统
公开(公告)号：US20130084008A1
公开(公告)日：2013-04-04
申请号：US13702700
申请日：2011-02-28
申请人： Gabriel Othmezouri , Ichiro Sakata , Roberto Cipolla , Vijay Badrinarayanan
发明人： Gabriel Othmezouri , Ichiro Sakata , Roberto Cipolla , Vijay Badrinarayanan
IPC分类号： G06K9/34
CPC分类号： G06K9/34 , G06K9/6297 , G06T7/11 , G06T7/143 , G06T2207/10016 , G06T2207/10024 , G06T2207/30232 , G06T2207/30236
摘要： A method (100) and system (300) is described for processing video data comprising a plurality of images. The method and apparatus is for obtaining for labelling of a plurality of objects or regions in an image of a sequence of images followed by label propagation to other images in the sequence based on an inference step and a model.
摘要翻译：描述了用于处理包括多个图像的视频数据的方法（100）和系统（300）。该方法和装置用于基于推理步骤和模型，获得图像序列的图像中的多个对象或区域的标记，然后按序列中的其他图像进行标签传播。

7. 发明申请

US20110292179A1 IMAGING SYSTEM AND METHOD 有权
标题翻译：成像系统和方法
公开(公告)号：US20110292179A1
公开(公告)日：2011-12-01
申请号：US13082833
申请日：2011-04-08
申请人： Carlos HERNANDEZ , George Vogiatzis , Roberto Cipolla
发明人： Carlos HERNANDEZ , George Vogiatzis , Roberto Cipolla
IPC分类号： H04N13/02 , G06T15/00
CPC分类号： G01B11/245 , G01B11/2545 , G06T7/521
摘要： According to one embodiment, an apparatus for determining the gradients of the surface normals of an object includes a receiving unit, establishing unit, determining unit, and selecting unit. The receiving unit is configured to receive data of three 2D images of the object, wherein each image is taken under illumination from a different direction. The establishing unit is configured to establish which pixels of the image are in shadow such that there is only data available from two images from these pixels. The determining unit is configured to determine a range of possible solutions for the gradient of the surface normal of a shadowed pixel using the data available for the two images. The selecting unit is configured to select a solution for the gradient using the integrability of the gradient field over an area of the object as a constraint and minimising a cost function.
摘要翻译：根据一个实施例，用于确定对象的表面法线的梯度的装置包括接收单元，建立单元，确定单元和选择单元。接收单元被配置为接收对象的三个2D图像的数据，其中每个图像在不同方向的照明下拍摄。建立单元被配置为确定图像的哪些像素处于阴影中，使得仅存在来自这些像素的两个图像的数据。确定单元被配置为使用可用于两个图像的数据来确定阴影像素的表面法线的梯度的可能解的范围。选择单元被配置为使用对象的区域上的梯度场的可整合性作为约束来选择用于梯度的解，并且最小化成本函数。

8. 发明申请

US20100128926A1 ITERATIVE MOTION SEGMENTATION 有权
标题翻译：迭代运动分类
公开(公告)号：US20100128926A1
公开(公告)日：2010-05-27
申请号：US11994748
申请日：2006-12-01
申请人： Masahiro Iwasaki , Arasanathan Thayananthan , Roberto Cipolla
发明人： Masahiro Iwasaki , Arasanathan Thayananthan , Roberto Cipolla
IPC分类号： G06K9/00
CPC分类号： G06K9/00335 , G06T7/215 , G06T7/277 , G06T2207/10016 , G06T2207/30241
摘要： An image processing device which simultaneously secures and extracts a background image, at least two object images, a shape of each object image and motion of each object image, from among plural images, the image processing device including an image input unit (101) which accepts input of plural images; a hidden parameter estimation unit (102) which estimates a hidden parameter based on the plural images and a constraint enforcement parameter, which indicates a condition of at least one of the hidden parameters, using an iterative learning method; a constraint enforcement parameter learning unit (103) which learns a constraint enforcement parameter related to the hidden parameter using an estimation result from the hidden parameter estimation unit as a training signal; and a complementary learning unit (104) which causes the estimation of the hidden parameter and the learning of the constraint enforcement parameter, which utilize the result from the learning of the hidden parameter, to be iterated.
摘要翻译：一种图像处理装置，其从多个图像中同时固定和提取背景图像，至少两个对象图像，每个对象图像的形状和每个对象图像的运动，所述图像处理装置包括图像输入单元（101），所述图像输入单元接受多幅图像的输入; 使用迭代学习方法，基于所述多个图像估计隐藏参数的隐藏参数估计单元（102）和指示所述隐藏参数中的至少一个的条件的约束强制参数; 约束执行参数学习单元，使用来自所述隐藏参数估计单元的估计结果作为训练信号来学习与所述隐藏参数相关的约束强制参数; 以及补充学习单元（104），其进行隐藏参数的估计和利用来自隐藏参数的学习的结果的约束强制参数的学习。

9. 发明授权

US07970205B2 Iterative motion segmentation 有权
标题翻译：迭代运动分割
公开(公告)号：US07970205B2
公开(公告)日：2011-06-28
申请号：US11994748
申请日：2006-12-01
申请人： Masahiro Iwasaki , Arasanathan Thayananthan , Roberto Cipolla
发明人： Masahiro Iwasaki , Arasanathan Thayananthan , Roberto Cipolla
IPC分类号： G06K9/62
CPC分类号： G06K9/00335 , G06T7/215 , G06T7/277 , G06T2207/10016 , G06T2207/30241
摘要： An image processing device which simultaneously secures and extracts a background image, at least two object images, a shape of each object image and motion of each object image, from among plural images, the image processing device including an image input unit (101) which accepts input of plural images; a hidden parameter estimation unit (102) which estimates a hidden parameter based on the plural images and a constraint enforcement parameter, which indicates a condition of at least one of the hidden parameters, using an iterative learning method; a constraint enforcement parameter learning unit (103) which learns a constraint enforcement parameter related to the hidden parameter using an estimation result from the hidden parameter estimation unit as a training signal; and a complementary learning unit (104) which causes the estimation of the hidden parameter and the learning of the constraint enforcement parameter, which utilize the result from the learning of the hidden parameter, to be iterated.
摘要翻译：一种图像处理装置，其从多个图像中同时固定和提取背景图像，至少两个对象图像，每个对象图像的形状和每个对象图像的运动，所述图像处理装置包括图像输入单元（101），所述图像输入单元接受多幅图像的输入; 使用迭代学习方法，基于所述多个图像估计隐藏参数的隐藏参数估计单元（102）和指示所述隐藏参数中的至少一个的条件的约束强制参数; 约束执行参数学习单元，使用来自所述隐藏参数估计单元的估计结果作为训练信号来学习与所述隐藏参数相关的约束强制参数; 以及补充学习单元（104），其进行隐藏参数的估计和利用来自隐藏参数的学习的结果的约束强制参数的学习。

10. 发明申请

US20110013840A1 IMAGE PROCESSING METHOD AND IMAGE PROCESSING APPARATUS 有权
标题翻译：图像处理方法和图像处理装置
公开(公告)号：US20110013840A1
公开(公告)日：2011-01-20
申请号：US12919849
申请日：2008-03-14
申请人： Masahiro Iwasaki , Arasanathan Thayananthan , Roberto Cipolla
发明人： Masahiro Iwasaki , Arasanathan Thayananthan , Roberto Cipolla
IPC分类号： G06K9/34
CPC分类号： G06T7/215 , G06T2207/10016 , G06T2207/30196
摘要： To provide an image processing apparatus which robustly performs segmentation on an image including an object such as a moving person with its deformation. The image processing apparatus includes: an image inputting unit (101) which receives temporally successive images; a motion analyzing unit (102) which calculates motions of blocks using at least two temporally different images and calculates, based on the motions of the blocks, temporal motion trajectories of the blocks in the temporally successive images; a distance calculating unit (103) which calculates a distance which indicates a similarity of the motions of the blocks, using a temporal motion trajectory of a block i and a temporal motion trajectory of a block other than the block i calculated by the motion analyzing unit; and a nonlinear space processing unit (104) which projects the distance calculated by the distance calculating unit into a nonlinear space and performs the segmentation on a result of the projection in the nonlinear space.
摘要翻译：提供一种图像处理装置，其对包括诸如移动人物的物体在其变形上的图像进行鲁棒地执行分割。图像处理装置包括：图像输入单元，其接收时间上连续的图像; 运动分析单元，其使用至少两个时间上不同的图像来计算块的运动，并且基于所述块的运动来计算所述时间上连续的图像中的块的时间运动轨迹; 距离计算单元，其使用块i的时间运动轨迹和运动分析单元计算的块i之外的块的时间运动轨迹来计算指示块的运动的相似度的距离; ; 以及非线性空间处理单元，其将由距离计算单元计算出的距离投影到非线性空间中，并且对非线性空间中的投影的结果进行分割。

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