-
公开(公告)号：KR20180056754A
公开(公告)日：2018-05-29
申请号：KR20187011521
申请日：2016-08-24
Applicant: QUALCOMM INC
Inventor： GALOR GLUSKIN MICHA , VELARDE RUBEN MANUEL , LEE JISOO
CPC classification number: G02B7/285 , G02B7/34 , G02B7/365 , H01L27/14621 , H01L27/14627 , H04N5/23212 , H04N5/3696 , H04N9/045 , H05K999/99
Abstract: 특정양태들은위상검출오토포커스에대해노이즈감소를수행하기위해이미징픽셀들 (즉, 비-위상검출픽셀들) 을이용하기위한시스템들및 기법들에관한것이다. 유리하게는, 이것은보다정확한위상검출오토포커스를제공하고, 또한위상검출을수행하기위한최적화된프로세서사용을제공할수 있다. 이미지포커스의시프트방향 (디포커스방향) 및시프트양 (디포커스양) 을나타내는위상차검출신호를획득하기위해위상차검출픽셀들이제공되고, 관심대상의인-포커스구역의포커스의레벨을추정하기위해서그리고식별된위상차를이에따라제한하기위해서이미징픽셀값들의분석이사용될수 있다.
-
公开(公告)号：ES2931984T3
公开(公告)日：2023-01-05
申请号：ES19769944
申请日：2019-08-30
Applicant: QUALCOMM INC
Inventor： GALOR GLUSKIN MICHA , LIU LEE-KANG , LEE JISOO
IPC: H04N13/239
-
公开(公告)号：CA3075544A1
公开(公告)日：2019-04-18
申请号：CA3075544
申请日：2018-10-05
Applicant: QUALCOMM INC
Inventor： HWANG HAU , PANKAJ TUSHAR SINHA , GUPTA VISHAL , LEE JISOO
IPC: G06T3/40
Abstract: Techniques and systems are provided for processing image data using one or more neural networks. For example, a patch of raw image data can be obtained. The patch can include a subset of pixels of a frame of raw image data, and the frame can be captured using one or more image sensors. The patch of raw image data includes a single color component for each pixel of the subset of pixels. At least one neural network can be applied to the patch of raw image data to determine a plurality of color component values for one or more pixels of the subset of pixels. A patch of output image data can then be generated based on application of the at least one neural network to the patch of raw image data. The patch of output image data includes a subset of pixels of a frame of output image data, and also includes the plurality of color component values for one or more pixels of the subset of pixels of the frame of output image data. Application of the at least one neural network causes the patch of output image data to include fewer pixels than the patch of raw image data. Multiple patches from the frame can be processed by the at least one neural network in order to generate a final output image. In some cases, the patches from the frame can be overlapping so that the final output image contains a complete picture.
-
公开(公告)号：AU2018346909A1
公开(公告)日：2020-03-26
申请号：AU2018346909
申请日：2018-10-05
Applicant: QUALCOMM INC
Inventor： HWANG HAU , PANKAJ TUSHAR SINHA , GUPTA VISHAL , LEE JISOO
IPC: G06T3/40
Abstract: Techniques and systems are provided for processing image data using one or more neural networks. For example, a patch of raw image data can be obtained. The patch can include a subset of pixels of a frame of raw image data, and the frame can be captured using one or more image sensors. The patch of raw image data includes a single color component for each pixel of the subset of pixels. At least one neural network can be applied to the patch of raw image data to determine a plurality of color component values for one or more pixels of the subset of pixels. A patch of output image data can then be generated based on application of the at least one neural network to the patch of raw image data. The patch of output image data includes a subset of pixels of a frame of output image data, and also includes the plurality of color component values for one or more pixels of the subset of pixels of the frame of output image data. Application of the at least one neural network causes the patch of output image data to include fewer pixels than the patch of raw image data. Multiple patches from the frame can be processed by the at least one neural network in order to generate a final output image. In some cases, the patches from the frame can be overlapping so that the final output image contains a complete picture.
-
-
-
Search Results
4
records
(took 0.022 seconds)
