-
公开(公告)号：US08989455B2
公开(公告)日：2015-03-24
申请号：US13751173
申请日：2013-01-28
申请人： Primesense Ltd.
发明人： Yael Shor , Tomer Yanir , Yaniv Shaked
CPC分类号： G06K9/00241 , G06K9/00201 , G06K9/00221 , G06T2207/10004 , G06T2207/30201
摘要： A method for face detection includes capturing a depth map and an image of a scene and selecting one or more locations in the image to test for presence of human faces. At each selected location, a respective face detection window is defined, having a size that is scaled according to a depth coordinate of the location that is indicated by the depth map. Apart of the image that is contained within each face detection window is processed to determine whether the face detection window contains a human face. Similar methods may also be applied in identifying other object types.
-
公开(公告)号：US20140333626A1
公开(公告)日：2014-11-13
申请号：US14341807
申请日：2014-07-27
申请人： PRIMESENSE LTD.
发明人： Amiad Gurman , Tomer Yanir , Michael Brand , Eran Guendelman
CPC分类号： G06T7/0053 , G06K9/00201 , G06K9/00362 , G06K9/00369 , G06T7/11 , G06T7/194 , G06T7/507 , G06T15/00 , G06T15/06 , G06T17/05 , G06T2207/10028 , G06T2215/12
摘要： A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.
摘要翻译： 一种处理数据的方法包括接收包含人形格式的场景的深度图。 处理深度图以识别场景中的三维（3D）连接分量，每个连接分量包括彼此相邻并具有相互相邻的深度值的一组像素。 单独的，第一和第二连接的部件被识别为属于类人形式，并且生成包括第一和第二连接部件两者的类人形状的表示。
-
公开(公告)号：US09002099B2
公开(公告)日：2015-04-07
申请号：US13786508
申请日：2013-03-06
申请人： Primesense Ltd.
发明人： Shai Litvak , Leonid Brailovsky , Tomer Yanir
IPC分类号： G06K9/00
CPC分类号： G06K9/00382 , G06K9/00201 , G06K9/4671
摘要： A method for processing data includes receiving a depth map of a scene containing a human hand, the depth map consisting of a matrix of pixels having respective pixel depth values. The method continues by extracting from the depth map respective descriptors based on the depth values in a plurality of patches distributed in respective positions over the human hand, and matching the extracted descriptors to previously-stored descriptors in a database. A pose of the human hand is estimated based on stored information associated with the matched descriptors.
摘要翻译： 一种处理数据的方法包括接收包含人手的场景的深度图，所述深度图由具有各自的像素深度值的像素矩阵组成。 该方法通过基于在人手上的相应位置中分布的多个补丁中的深度值从深度图相应的描述符提取，并且将所提取的描述符与先前存储的描述符匹配在数据库中。 基于与匹配描述符相关联的存储信息来估计人的手势。
-
公开(公告)号：US08781217B2
公开(公告)日：2014-07-15
申请号：US13867083
申请日：2013-04-21
申请人： Primesense Ltd.
发明人： Amiad Gurman , Tomer Yanir , Michael Brand , Eran Guendelman
CPC分类号： G06T7/0053 , G06K9/00201 , G06K9/00362 , G06K9/00369 , G06T7/11 , G06T7/194 , G06T7/507 , G06T15/00 , G06T15/06 , G06T17/05 , G06T2207/10028 , G06T2215/12
摘要： A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.
摘要翻译： 一种处理数据的方法包括接收包含人形格式的场景的深度图。 处理深度图以识别场景中的三维（3D）连接分量，每个连接分量包括彼此相邻并具有相互相邻深度值的一组像素。 单独的，第一和第二连接的部件被识别为属于类人形式，并且生成包括第一和第二连接部件两者的类人形状的表示。
-
公开(公告)号：US20130236089A1
公开(公告)日：2013-09-12
申请号：US13786508
申请日：2013-03-06
申请人： PRIMESENSE LTD.
发明人： Shai Litvak , Leonid Brailovsky , Tomer Yanir
IPC分类号： G06K9/00
CPC分类号： G06K9/00382 , G06K9/00201 , G06K9/4671
摘要： A method for processing data includes receiving a depth map of a scene containing a human hand, the depth map consisting of a matrix of pixels having respective pixel depth values. The method continues by extracting from the depth map respective descriptors based on the depth values in a plurality of patches distributed in respective positions over the human hand, and matching the extracted descriptors to previously-stored descriptors in a database. A pose of the human hand is estimated based on stored information associated with the matched descriptors.
摘要翻译： 一种处理数据的方法包括接收包含人手的场景的深度图，所述深度图由具有各自的像素深度值的像素矩阵组成。 该方法通过基于在人手上的相应位置中分布的多个补丁中的深度值从深度图相应的描述符提取，并且将所提取的描述符与先前存储的描述符匹配在数据库中。 基于与匹配描述符相关联的存储信息来估计人的手势。
-
公开(公告)号：US20130230215A1
公开(公告)日：2013-09-05
申请号：US13867085
申请日：2013-04-21
申请人： PRIMESENSE LTD.
发明人： Amiad Gurman , Tomer Yanir , Michael Brand , Eran Guendelman
CPC分类号： G06T7/0053 , G06K9/00201 , G06K9/00362 , G06K9/00369 , G06T7/11 , G06T7/194 , G06T7/507 , G06T15/00 , G06T15/06 , G06T17/05 , G06T2207/10028 , G06T2215/12
摘要： A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.
摘要翻译： 一种处理数据的方法包括接收包含人形格式的场景的深度图。 处理深度图以识别场景中的三维（3D）连接分量，每个连接分量包括彼此相邻并具有相互相邻的深度值的一组像素。 单独的，第一和第二连接的部件被识别为属于类人形式，并且生成包括第一和第二连接部件两者的类人形状的表示。
-
公开(公告)号：US08824737B2
公开(公告)日：2014-09-02
申请号：US13867085
申请日：2013-04-21
申请人： Primesense Ltd.
发明人： Amiad Gurman , Tomer Yanir , Michael Brand , Eran Guendelman
CPC分类号： G06T7/0053 , G06K9/00201 , G06K9/00362 , G06K9/00369 , G06T7/11 , G06T7/194 , G06T7/507 , G06T15/00 , G06T15/06 , G06T17/05 , G06T2207/10028 , G06T2215/12
摘要： A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.
摘要翻译： 一种处理数据的方法包括接收包含人形格式的场景的深度图。 处理深度图以识别场景中的三维（3D）连接分量，每个连接分量包括彼此相邻并具有相互相邻的深度值的一组像素。 单独的，第一和第二连接的部件被识别为属于类人形式，并且生成包括第一和第二连接部件两者的类人形状的表示。
-
公开(公告)号：US09460339B2
公开(公告)日：2016-10-04
申请号：US14304939
申请日：2014-06-15
申请人： PrimeSense Ltd.
发明人： Shai Litvak , Tomer Yanir , Eran Guendelman
CPC分类号： G06K9/00355 , G06K9/00375 , G06K9/6289 , G06T7/248 , G06T7/277 , G06T7/521 , G06T7/73 , G06T7/90 , G06T2207/10016 , G06T2207/10024 , G06T2207/10028 , G06T2207/20076 , G06T2207/30196 , G06T2207/30241
摘要： A method for image processing includes receiving a depth image of a scene containing a human subject and receiving a color image of the scene containing the human subject. A part of a body of the subject is identified in at least one of the images. A quality of both the depth image and the color image is evaluated, and responsively to the quality, one of the images is selected to be dominant in processing of the part of the body in the images. The identified part is localized in the dominant one of the images, while using supporting data from the other one of the images.
摘要翻译： 一种用于图像处理的方法包括：接收包含人类对象的场景的深度图像，并接收包含人类对象的场景的彩色图像。 在至少一个图像中识别对象的身体的一部分。 评估深度图像和彩色图像的质量，并且响应于质量，在处理图像中的身体的一部分时，选择一个图像占主导地位。 识别的部分被定位在主要图像之一中，同时使用来自另一个图像的支持数据。
-
公开(公告)号：US09196045B2
公开(公告)日：2015-11-24
申请号：US14341807
申请日：2014-07-27
申请人： PRIMESENSE LTD.
发明人： Amiad Gurman , Tomer Yanir , Michael Brand , Eran Guendelman
CPC分类号： G06T7/0053 , G06K9/00201 , G06K9/00362 , G06K9/00369 , G06T7/11 , G06T7/194 , G06T7/507 , G06T15/00 , G06T15/06 , G06T17/05 , G06T2207/10028 , G06T2215/12
摘要： A method for processing data includes receiving a depth map of a scene containing a humanoid form. The depth map is processed so as to identify three-dimensional (3D) connected components in the scene, each connected component including a set of the pixels that are mutually adjacent and have mutually-adjacent depth values. Separate, first and second connected components are identified as both belonging to the humanoid form, and a representation of the humanoid form is generated including both of the first and second connected components.
摘要翻译： 一种处理数据的方法包括接收包含人形格式的场景的深度图。 处理深度图以识别场景中的三维（3D）连接分量，每个连接分量包括彼此相邻并具有相互相邻的深度值的一组像素。 单独的，第一和第二连接的部件被识别为属于类人形式，并且生成包括第一和第二连接部件两者的类人形状的表示。
-
公开(公告)号：US20140294237A1
公开(公告)日：2014-10-02
申请号：US14304939
申请日：2014-06-15
申请人： PrimeSense Ltd.
发明人： Shai Litvak , Tomer Yanir , Eran Guendelman
CPC分类号： G06K9/00355 , G06K9/00375 , G06K9/6289 , G06T7/248 , G06T7/277 , G06T7/521 , G06T7/73 , G06T7/90 , G06T2207/10016 , G06T2207/10024 , G06T2207/10028 , G06T2207/20076 , G06T2207/30196 , G06T2207/30241
摘要： A method for image processing includes receiving a depth image of a scene containing a human subject and receiving a color image of the scene containing the human subject. A part of a body of the subject is identified in at least one of the images. A quality of both the depth image and the color image is evaluated, and responsively to the quality, one of the images is selected to be dominant in processing of the part of the body in the images. The identified part is localized in the dominant one of the images, while using supporting data from the other one of the images.
摘要翻译： 一种用于图像处理的方法包括：接收包含人类对象的场景的深度图像，并接收包含人类对象的场景的彩色图像。 在至少一个图像中识别对象的身体的一部分。 评估深度图像和彩色图像的质量，并且响应于质量，在处理图像中的身体的一部分时，选择一个图像占主导地位。 识别的部分被定位在主要图像之一中，同时使用来自另一个图像的支持数据。
-
-
-
-
-
-
-
-
-
搜索结果
12 条记录 (耗时 0.019 秒)
