-
公开(公告)号：US12002259B2
公开(公告)日：2024-06-04
申请号：US17149772
申请日：2021-01-15
Applicant: CANON KABUSHIKI KAISHA
Inventor： Masato Aoba , Koichi Magai
IPC: G06V10/82 , G06F18/2115 , G06F18/2411 , G06F18/2413 , G06F18/2431 , G06T7/11 , G06T7/12 , G06V10/764 , G06V30/19 , G06V30/194
CPC classification number: G06V10/82 , G06F18/2115 , G06F18/2411 , G06F18/2414 , G06F18/2431 , G06T7/11 , G06T7/12 , G06V10/764 , G06V30/19173 , G06V30/194 , G06T2207/10024 , G06T2207/20021 , G06T2207/20081 , G06T2207/20084 , G06T2207/30201 , G06V2201/07
Abstract: There is provided with an image processing apparatus, for example, for image recognition. An extraction unit extracts a feature amount from a target image. An estimation unit estimates distribution of regions having attributes different from each other in the target image based on the feature amount.
-
2.发明申请
公开(公告)号：US20200007781A1
公开(公告)日：2020-01-02
申请号：US16447676
申请日：2019-06-20
Applicant: CANON KABUSHIKI KAISHA
Inventor： Masato Aoba
Abstract: An imaging apparatus configured to estimate information about an imaging setting of the imaging apparatus by using a trained model. The imaging apparatus includes a detection unit configured to detect a first operation for finalizing imaging and a second operation for interrupting imaging of the imaging apparatus in which the imaging setting has been made based on the information estimated by the trained model, and a training unit configured to update a connection weight of the trained model through reinforcement learning by determining, when the first operation is detected by the detection unit, a positive reward, and when the second operation is detected by the detection unit, a negative reward for the information having been estimated when the first or second operation is detected by the detection unit.
-
3.发明申请
公开(公告)号：US20190012790A1
公开(公告)日：2019-01-10
申请号：US16022975
申请日：2018-06-29
Applicant: CANON KABUSHIKI KAISHA
Inventor： Masato Aoba , Koichi Magai
Abstract: There is provided with an image processing apparatus, for example, for image recognition. An extraction unit extracts a feature amount from a target image. An estimation unit estimates distribution of regions having attributes different from each other in the target image based on the feature amount.
-
公开(公告)号：US20190114508A1
公开(公告)日：2019-04-18
申请号：US16215425
申请日：2018-12-10
Applicant: CANON KABUSHIKI KAISHA
Inventor： Masato Aoba
CPC classification number: G06K9/6255 , B25J9/1697 , G06K9/00208 , G06K9/4661 , G06K2209/19 , G06T7/0004 , G06T7/74 , G06T7/75 , G06T2207/20081
Abstract: In a case where generating a training image of an object to be used to generate a dictionary to be referred to in image recognition processing of detecting the object from an input image, model information of an object to be detected is set, and a luminance image of the object and a range image are input. The luminance distribution of the surface of the object is estimated based on the luminance image and the range image, and the training image of the object is generated based on the model information and the luminance distribution.
-
公开(公告)号：US20140294292A1
公开(公告)日：2014-10-02
申请号：US14204198
申请日：2014-03-11
Applicant: Canon Kabushiki Kaisha
Inventor： Masato Aoba
IPC: G06K9/62
CPC classification number: G06K9/6255 , B25J9/1697 , G06K9/00208 , G06K9/4661 , G06K2209/19 , G06T7/0004 , G06T7/74 , G06T7/75 , G06T2207/20081
Abstract: In a case where generating a training image of an object to be used to generate a dictionary to be referred to in image recognition processing of detecting the object from an input image, model information of an object to be detected is set, and a luminance image of the object and a range image are input. The luminance distribution of the surface of the object is estimated based on the luminance image and the range image, and the training image of the object is generated based on the model information and the luminance distribution.
Abstract translation: 在从输入图像检测对象的图像识别处理中生成要用于生成要引用的字典的对象的训练图像的情况下，设置要检测的对象的模型信息，并且设置亮度图像 并输入范围图像。 基于亮度图像和范围图像来估计对象的表面的亮度分布，并且基于模型信息和亮度分布来生成对象的训练图像。
-
公开(公告)号：US20140198951A1
公开(公告)日：2014-07-17
申请号：US14152121
申请日：2014-01-10
Applicant: CANON KABUSHIKI KAISHA
Inventor： Masato Aoba , Takayuki Saruta
CPC classification number: G06K9/6807 , G06K9/00664
Abstract: A dictionary for detection of an object is created from an image obtained by performing an image process, which depends on a first image process parameter, on the training image of the detection target object. The dictionary created based on the image process depending on the first image process parameter is determined, based on a result of detecting the object from an image obtained by performing an image process, which depends on the first image process parameter, on a photographed image based on the dictionary. A second image process parameter is determined, based on a result of detecting the object from an image obtained by performing an image process, which depends on the second image process parameter, on the photographed image using the determined dictionary.
Abstract translation: 用于检测对象的字典是根据检测目标对象的训练图像执行取决于第一图像处理参数的图像处理而获得的图像来创建的。 基于从基于第一图像处理参数执行图像获得的图像检测对象的结果，基于基于第一图像处理参数的图像处理而创建的字典基于所拍摄的图像被确定 在字典上。 基于通过使用确定的字典对拍摄的图像执行依赖于第二图像处理参数的图像处理获得的图像来检测对象的结果来确定第二图像处理参数。
-
公开(公告)号：US20220086359A1
公开(公告)日：2022-03-17
申请号：US17405167
申请日：2021-08-18
Applicant: CANON KABUSHIKI KAISHA
Inventor： Masato Aoba , Koichi Takeuchi
Abstract: An image processing apparatus is operable to determine a focus target area of an image capturing apparatus. The apparatus comprises: an obtainment unit configured to obtain a first area to be a focus target in a first image captured by the image capturing apparatus at a first point in time, a detection unit configured to detect a second area to be a focus target candidate from a second image captured by the image capturing apparatus at a second point in time succeeding a first point in time; and a determination unit configured to determine, based on the first area and the second image, a focus target area in the second image from among one or more partial areas in the second area.
-
公开(公告)号：US11165948B2
公开(公告)日：2021-11-02
申请号：US16447676
申请日：2019-06-20
Applicant: CANON KABUSHIKI KAISHA
Inventor： Masato Aoba
Abstract: An imaging apparatus configured to estimate information about an imaging setting of the imaging apparatus by using a trained model. The imaging apparatus includes a detection unit configured to detect a first operation for finalizing imaging and a second operation for interrupting imaging of the imaging apparatus in which the imaging setting has been made based on the information estimated by the trained model, and a training unit configured to update a connection weight of the trained model through reinforcement learning by determining, when the first operation is detected by the detection unit, a positive reward, and when the second operation is detected by the detection unit, a negative reward for the information having been estimated when the first or second operation is detected by the detection unit.
-
公开(公告)号：US10929978B2
公开(公告)日：2021-02-23
申请号：US16022975
申请日：2018-06-29
Applicant: CANON KABUSHIKI KAISHA
Inventor： Masato Aoba , Koichi Magai
Abstract: There is provided with an image processing apparatus, for example, for image recognition. An extraction unit extracts a feature amount from a target image. An estimation unit estimates distribution of regions having attributes different from each other in the target image based on the feature amount.
-
公开(公告)号：US10395136B2
公开(公告)日：2019-08-27
申请号：US14849346
申请日：2015-09-09
Applicant: CANON KABUSHIKI KAISHA
Inventor： Masato Aoba
Abstract: An image processing apparatus includes a first learning unit configured to learn an identifier for identifying a class of a region formed by segmenting an image based on first training data, an evaluation unit configured to evaluate a result of identification of a class of the first training data by the identifier, a generation unit configured to generate second training data from the first training data based on an evaluation result by the evaluation unit, and a second learning unit configured to learn a plurality of identifiers different from the identifier learned by the first learning unit based on the second training data.
