-
公开(公告)号：US11669939B1
公开(公告)日：2023-06-06
申请号：US17000832
申请日：2020-08-24
Applicant: GoPro, Inc.
CPC classification number: G06T5/003 , G06N3/045 , G06N3/08 , G06N20/10 , G06T3/4084 , G06T5/50 , G06T7/11 , G06T2207/10024 , G06T2207/20056 , G06T2207/20084 , G06T2207/20112 , G06T2207/20201
Abstract: A method for deblurring a target image includes receiving a burst of images that includes the target image; partitioning respective images of the burst of images into respective patches; converting, to a frequency domain, the respective patches into respective transform patches; selecting a first set of corresponding transform patches from the respective transform patches, where the first set of the corresponding transform patches includes a respective transform patch for a respective image of the burst of images; obtaining, using a neural network, respective weight maps for the corresponding transform patches; obtaining a deblurred transform patch by combining the first set of corresponding transform patches using the respective weight maps; obtaining a first deblurred patch by converting the deblurred transform patch to a pixel domain; and obtaining a deblurred image of the target image using the first deblurred patch.
-
22.发明申请公开(公告)号：US20190132519A1
公开(公告)日：2019-05-02
申请号：US16233914
申请日：2018-12-27
Applicant: Fatih M. Ozluturk
Inventor： Fatih M. Ozluturk
CPC classification number: H04N5/23287 , G02B27/646 , G06T5/002 , G06T5/003 , G06T7/20 , G06T2207/10004 , G06T2207/10016 , G06T2207/20024 , G06T2207/20201 , G06T2207/20212 , H04N5/23216 , H04N5/23229 , H04N5/23248 , H04N5/23251 , H04N5/23254 , H04N5/23258 , H04N5/23267 , H04N5/23293 , H04N5/265
Abstract: A method and apparatus for use in a digital imaging device for correcting image blur in digital images by combining plurality of images. The plurality of images that are combined include a main subject that can be selected by user input or automatically by the digital imaging device. Blur correction can be performed to make the main subject blur-free while the rest of the image is blurred. All of the image may be made blur-free or the main subject can be made blur-free at the expense of the rest of the image. Result is a blur corrected image that is recorded in a memory.
-
公开(公告)号：US20190052809A1
公开(公告)日：2019-02-14
申请号：US16053931
申请日：2018-08-03
Applicant: CANON KABUSHIKI KAISHA
Inventor： Hitoshi Miyazawa
CPC classification number: H04N5/23267 , G01P3/68 , G06T5/003 , G06T7/20 , G06T7/254 , G06T7/40 , G06T7/70 , G06T2207/20021 , G06T2207/20201 , H04N5/23209 , H04N5/23254 , H04N5/23258 , H04N5/23261 , H04N5/2327
Abstract: An imaging apparatus includes an angular velocity sensor configured to detect shaking and a motion vector detection unit configured to detect movement in a captured image. A shift lens group constitutes a correction optical system configured to correct an image blur due to shaking exerted on the imaging apparatus. A position sensor detects a position of the shift lens group. A distance acquiring unit acquires distance information associated with the captured image. When an angular velocity of an object is calculated on the basis of a shaking detection signal, a movement vector, position information of the shift lens group, and the distance information, an object angular velocity calculating unit calculates an amount of movement of the object by adding position information of the shift lens group synchronized with a detection period of the movement vector to movement vector information and calculates an amount of shaking correction.
-
24.发明申请公开(公告)号：US20180302554A1
公开(公告)日：2018-10-18
申请号：US15960168
申请日：2018-04-23
Applicant: FotoNation Cayman Limited
Inventor： Dan Lelescu , Thang Duong
CPC classification number: H04N5/23232 , G06T5/003 , G06T7/20 , G06T7/80 , G06T2200/21 , G06T2207/10028 , G06T2207/10052 , G06T2207/20201 , G06T2207/20221 , H04N5/2226 , H04N5/2258 , H04N5/23251 , H04N5/23258 , H04N5/23264 , H04N5/35545
Abstract: Systems and methods for synthesizing high resolution images using image deconvolution and depth information in accordance embodiments of the invention are disclosed. In one embodiment, an array camera includes a processor and a memory, wherein an image deconvolution application configures the processor to obtain light field image data, determine motion data based on metadata contained in the light field image data, generate a depth-dependent point spread function based on the synthesized high resolution image, the depth map, and the motion data, measure the quality of the synthesized high resolution image based on the generated depth-dependent point spread function, and when the measured quality of the synthesized high resolution image is within a quality threshold, incorporate the synthesized high resolution image into the light field image data.
-
公开(公告)号：US20180268215A1
公开(公告)日：2018-09-20
申请号：US15968578
申请日：2018-05-01
Applicant: Samsung Electronics Co., Ltd.
Inventor： Ilia Ovsiannikov , Yibing Michelle Wang , Yong-Hwa Park , Yong-Chul Cho , Heesun Yoon , ChangYoung Park , Dirk Smits
CPC classification number: G06K9/00604 , G06F21/32 , G06K9/00033 , G06K9/00617 , G06K9/4609 , G06T7/586 , G06T2207/20201 , G07C9/00158
Abstract: Exemplary embodiments for a biometric camera system for a mobile device, comprise: a near infrared (NIR) light source on the mobile device that flashes a user of the mobile device with near infrared light during image capture; a biometric camera located on the mobile device offset from the NIR light source, the biometric camera comprising: an extended depth of field (EDOF) imaging lens; a bandpass filter located adjacent to the EDOF imaging lens to reject ambient light during image capture; and an imaging sensor located adjacent the bandpass filter that converts an optical image of an object into an electronic signal for image processing; and a processor configured to receive video images of an iris of a user from the image sensor, and attempt to match the video images of the iris with previously registered images stored in an iris database, wherein if a match is found, the user is authenticated.
-
Patent Agency Ranking
公开(公告)号：US20180247423A1
公开(公告)日：2018-08-30
申请号：US15754162
申请日：2016-08-08
Applicant: Mitsubishi Electric Corporation
Inventor： Daisuke SUZUKI , Takeo FUJITA , Toru AOKI , Narihiro MATOBA
CPC classification number: G06T7/536 , G06T5/003 , G06T5/50 , G06T7/579 , G06T2207/10016 , G06T2207/20201 , G06T2207/30252
Abstract: An image processing device is provided with an optical flow calculation circuit (101) for calculating a plurality of optical flows between a first image and a second image captured before the first image, a vector decomposition circuit (102) for decomposing each of the optical flows into a vanishing point direction vector and an orthogonal vector, a vibration blur amount calculation circuit (103) for calculating the aggregate values of horizontal and vertical components of the orthogonal vector and calculating the amount of vibration blur of the first image based on the aggregate values, an optical flow starting point correction circuit (104) for correcting the calculated optical flows by the amount of vibration blur, and a vanishing point calculation circuit (105) for calculating a vanishing point of the first image based on the corrected optical flows.
-
27.发明授权公开(公告)号：US10063779B2
公开(公告)日：2018-08-28
申请号：US15427383
申请日：2017-02-08
Applicant: CANON KABUSHIKI KAISHA
Inventor： Fumiaki Takahashi
CPC classification number: H04N5/23267 , G06T5/003 , G06T5/50 , G06T2207/10016 , G06T2207/10024 , G06T2207/20182 , G06T2207/20201 , G06T2207/20221 , H04N5/23254 , H04N5/23261
Abstract: An image processing apparatus comprises the following units. A dividing unit divides a frame of a moving image into a changing area in which there is an active object and a changeless area in which there is a stationary object. A generation unit generates a still image by compositing an area corresponding to the changeless area in each of X frame(s) (where X is an integer of 1 or more) among a plurality of frames included in the moving image and an area corresponding to the changing area in each of Y frames (where Y is an integer greater than X) among the plurality of frames.
-
公开(公告)号：US20180189943A1
公开(公告)日：2018-07-05
申请号：US15909600
申请日：2018-03-01
Applicant: FUJITSU LIMITED
Inventor： TAKASHI FUSE , Tetsuo Koezuka
CPC classification number: G06T7/0002 , G06K9/00771 , G06T5/003 , G06T7/001 , G06T2207/20201 , G06T2207/30108 , H04N5/144 , H04N5/232 , H04N5/23229 , H04N5/23264
Abstract: An abnormal detection apparatus including an imaging unit configured to image generate a first and second image frames included in a first image frame group; a pseudo work generation unit configured to generate the first and a third image frames, the third and the second image frames, or the third and a fourth image frames, included in a second image frame group, respectively, with respect to the first and second image frames included in the first image frame group; a normal space generation unit configured to generate a normal space data based on the first and second image frames included in the first image frame group, and the first and third image frames, the third and second image frames, or the third and fourth image frames, included in the second image frame group; and a comparison unit configured to detect abnormality based on the normal space data.
-
公开(公告)号：US20180182077A1
公开(公告)日：2018-06-28
申请号：US15901031
申请日：2018-02-21
Applicant: NIKON CORPORATION
Inventor： Radka Tezaur
CPC classification number: G06T5/003 , G06T5/20 , G06T5/50 , G06T2207/20192 , G06T2207/20201
Abstract: A method for deblurring a blurry image (400) includes the steps of: performing a first phase of deconvolution (202) with a first phase regularization spatial mask (300) to reconstruct the main edges and generate a first phase latent sharp image (404) having reconstructed main edges; and performing a second phase of deconvolution (204) with a second phase regularization spatial mask (304) to reconstruct the texture and generate a second phase latent sharp image (406). The second phase regularization spatial mask (304) can be different from the first phase regularization spatial mask (300).
-
公开(公告)号：US09998666B2
公开(公告)日：2018-06-12
申请号：US15248895
申请日：2016-08-26
Applicant: Duke University
Inventor： Guillermo Sapiro , Mauricio Delbracio
CPC classification number: H04N5/23267 , G06T5/003 , G06T5/20 , G06T5/50 , G06T2207/10016 , G06T2207/10024 , G06T2207/20056 , G06T2207/20182 , G06T2207/20201 , G06T2207/20221 , H04N5/23245 , H04N5/23254 , H04N5/23258
Abstract: System and Method for automatically removing blur and noise in a plurality of digital images. The system comprises an electronic processor configured to receive the plurality of digital images, perform motion estimation and motion compensation to align the plurality of digital images, determine an alignment of the plurality of digital images with respect to a reference frame, generate a consistency map based on the alignment of the plurality of digital images with respect to the reference frame, combine the plurality of digital images aligned with respect to the reference frame in the Fourier domain using a quality of alignment information from the consistency map to generate an aggregated frame, and apply a post-processing filter to enhance the quality of the aggregated frame.
-
-
-
-
-
-
-
-
-
Search Results
1174
records
(took 0.028 seconds)
