-
公开(公告)号：US10115208B2
公开(公告)日：2018-10-30
申请号：US15355324
申请日：2016-11-18
Applicant: Huawei Technologies Co., Ltd.
Inventor： Wanli Ouyang , Xiao Chu , Wenqi Ju , Jianzhuang Liu , Xiaogang Wang
Abstract: An image characteristic estimation method and device is presented, where content of the method includes extracting at least two eigenvalues of input image data, and executing the following operations for each extracted eigenvalue, until execution for the extracted eigenvalues is completed. Selecting an eigenvalue, and performing at least two matrix transformations on the eigenvalue using a pre-obtained matrix parameter in order to obtain a first matrix vector corresponding to the eigenvalue; when a first matrix vector corresponding to each extracted eigenvalue is obtained, obtaining second matrix vectors with respect to the at least two extracted eigenvalues using a convolutional network calculation method according to the obtained first matrix vector corresponding to each eigenvalue; and obtaining a status of an image characteristic in the image data by means of estimation according to the second matrix vectors. In this way, accuracy of estimation is effectively improved.
-
公开(公告)号：US20170069112A1
公开(公告)日：2017-03-09
申请号：US15355324
申请日：2016-11-18
Applicant: Huawei Technologies Co., Ltd.
Inventor： Wanli Ouyang , Xiao Chu , Wenqi Ju , Jianzhuang Liu , Xiaogang Wang
IPC: G06T7/60
CPC classification number: G06T7/60 , G06K9/00362 , G06K9/4628 , G06K9/6214 , G06K9/6247 , G06K9/629 , G06T7/00 , G06T2207/10004
Abstract: An image characteristic estimation method and device is presented, where content of the method includes extracting at least two eigenvalues of input image data, and executing the following operations for each extracted eigenvalue, until execution for the extracted eigenvalues is completed. Selecting an eigenvalue, and performing at least two matrix transformations on the eigenvalue using a pre-obtained matrix parameter in order to obtain a first matrix vector corresponding to the eigenvalue; when a first matrix vector corresponding to each extracted eigenvalue is obtained, obtaining second matrix vectors with respect to the at least two extracted eigenvalues using a convolutional network calculation method according to the obtained first matrix vector corresponding to each eigenvalue; and obtaining a status of an image characteristic in the image data by means of estimation according to the second matrix vectors. In this way, accuracy of estimation is effectively improved.
Abstract translation: 提出了一种图像特征估计方法和装置，其中方法的内容包括提取输入图像数据的至少两个特征值，并且对于每个提取的特征值执行以下操作，直到完成提取的特征值的执行。 选择特征值，并使用预先获得的矩阵参数在特征值上执行至少两个矩阵变换，以便获得对应于特征值的第一矩阵向量; 当获得与每个提取的特征值对应的第一矩阵向量时，使用根据所获得的与每个特征值对应的第一矩阵向量的卷积网络计算方法获得关于所述至少两个提取的特征值的第二矩阵向量; 以及通过根据第二矩阵向量的估计来获得图像数据中的图像特性的状态。 以这种方式，有效地提高了估计的准确性。
-
公开(公告)号：US10115009B2
公开(公告)日：2018-10-30
申请号：US15289450
申请日：2016-10-10
Applicant: Huawei Technologies Co., Ltd.
Inventor： Xiao Chu , Wanli Ouyang , Xiaogang Wang , Wei Li , Jianzhuang Liu
Abstract: A body relationship estimation method and apparatus are disclosed. The method includes obtaining a target picture, calculating a first body relationship feature of two persons according to at least one of first location information of a body part of each person of the two persons in the target picture or second location information of body parts of the two persons, where the first location information is obtained by performing single-person gesture estimation on each person, and the second location information is obtained by performing two-person joint gesture estimation on the two persons when the first location information indicates that the body parts of the two persons overlap, and determining a body relationship between the two persons according to the first body relationship feature.
-
公开(公告)号：US20170154213A1
公开(公告)日：2017-06-01
申请号：US15289450
申请日：2016-10-10
Applicant: Huawei Technologies Co., Ltd.
Inventor： Xiao Chu , Wanli Ouyang , Xiaogang Wang , Wei Li , Jianzhuang Liu
CPC classification number: G06K9/00375 , G06K9/00335 , G06K9/4628 , G06K9/6202 , G06K9/6215 , G06K9/66
Abstract: A body relationship estimation method and apparatus are disclosed. The method includes obtaining a target picture, calculating a first body relationship feature of two persons according to at least one of first location information of a body part of each person of the two persons in the target picture or second location information of body parts of the two persons, where the first location information is obtained by performing single-person gesture estimation on each person, and the second location information is obtained by performing two-person joint gesture estimation on the two persons when the first location information indicates that the body parts of the two persons overlap, and determining a body relationship between the two persons according to the first body relationship feature.
-
-
-
Search Results
4
records
(took 0.019 seconds)
