-
公开(公告)号：US09635389B1
公开(公告)日：2017-04-25
申请号：US14953850
申请日：2015-11-30
Applicant: Amazon Technologies, Inc.
Inventor： Ilya Vladimirovich Brailovskiy , Ilia Vitsnudel
IPC: G06K9/46 , H04N19/93 , H04N19/182 , H04N19/176 , H04N19/117 , H04N19/12 , H04N19/186 , H04N19/15 , H04N19/152
CPC classification number: H04N19/93 , H04N19/117 , H04N19/119 , H04N19/12 , H04N19/136 , H04N19/15 , H04N19/152 , H04N19/176 , H04N19/182 , H04N19/186 , H04N19/593
Abstract: Various examples are directed to methods and systems for compressing a binary mask. A computer device may determine that a frequency of a less frequent pixel value state of the binary mask is less than a threshold frequency and may select a block size corresponding to the threshold frequency. The computing device may determine a first run length number of pixel value blocks of the block size that are positioned consecutively in the binary mask sequence and that comprise a first pattern of pixel values and write the first run length number to a first compression sequence.
-
公开(公告)号：US10210627B1
公开(公告)日：2019-02-19
申请号：US15413255
申请日：2017-01-23
Applicant: Amazon Technologies, Inc.
Inventor： Ilia Vitsnudel , Ilya Vladimirovich Brailovskiy
Abstract: A computer system determines a metric for an input object, which could be an image of a person with the metric being measure of the person's body size, age, etc. A paired neural network system is trained on a training set of objects having pairs of objects each assigned a relative metric. A relative metric for a pair indicate which of the pair has the higher metric. A representative set of objects includes a known assigned metric value for each object. The trained paired neural network system pairwise compares an input object with objects from the representative set to determine a relative metric for each such pair, to arrive at a collection of relative metrics of the input object relative to various objects in the representative set. A metric value can be estimated for the input object based on the collection of relative metrics and those known metric values.
-
公开(公告)号：US10063792B1
公开(公告)日：2018-08-28
申请号：US14870935
申请日：2015-09-30
Applicant: Amazon Technologies, Inc.
Inventor： Ilya Vladimirovich Brailovskiy , Ilia Vitsnudel , Philip James Taylor , Nathaniel Bubis , Matthew Alan Townsend , Dmitry Svetlov , Noam Sorek , Benjamin Robert Hirsch , Paul Andersen Alioshin
CPC classification number: H04N5/2628 , H04N5/2258 , H04N5/23238 , H04N7/181
Abstract: Various examples are directed to systems and methods for formatting stitched panoramic frames for transmission to a remote image processing system, the method comprising. A control circuit of a panoramic camera may receive first and second frames captured by first and second image sensors having partially overlapping fields-of-view. The control circuit may identify a first overlap region of the first frame and a second overlap region of the second frame. The first and second overlap region may comprise pixel values from portions of the fields-of-view of the image sensors that overlap. The control circuit may generate a panoramic frame from based at least in part on the first and second frames. The control circuit may generate a transmission frame comprising the panoramic frame, the first overlap region and the second overlap region.
-
公开(公告)号：US09892488B1
公开(公告)日：2018-02-13
申请号：US14838863
申请日：2015-08-28
Applicant: Amazon Technologies, Inc.
Inventor： Ilya Vladimirovich Brailovskiy , Ilia Vitsnudel
CPC classification number: G06T3/4038 , G06T5/009 , G06T5/50 , G06T7/337 , G06T2200/32 , G06T2207/10012 , G06T2207/10024 , G06T2207/20016 , G06T2207/20208 , G06T2207/20221 , H04N5/2253 , H04N5/2258 , H04N5/23229 , H04N5/23238
Abstract: Various examples are directed to an image processing system comprising a mounting assembly, a first image sensor, a second image sensor, and a third image sensor. A processor may be programmed to receive, from the first image sensor, a first frame, receive, from the third image sensor, a third frame, and identify a first optical flow from the first frame to the third frame. Based at least in part on the first optical flow, the processor may generate a translation kernel describing a first translation from a first position of the first frame to a destination position, and apply the translation kernel to generate a translated first frame.
-
公开(公告)号：US09842254B1
公开(公告)日：2017-12-12
申请号：US14868134
申请日：2015-09-28
Applicant: Amazon Technologies, Inc.
Inventor： Ilya Vladimirovich Brailovskiy , Ilia Vitsnudel
CPC classification number: G06K9/00577 , G06K2009/00583 , G06T7/246 , G06T2207/10021 , H04N5/2258 , H04N5/23238 , H04N7/181
Abstract: The systems and/or processes described herein may calibrate an inertial measurement unit (IMU) of an electronic device in part by using images captured by one or more cameras of the electronic device. In this regard, an IMU of an electronic device may comprise a gyroscope, an accelerometer, a magnetometer, or any other type of motion sensor or rotational sensor.
-
Patent Agency Ranking
公开(公告)号：US11961601B1
公开(公告)日：2024-04-16
申请号：US16919870
申请日：2020-07-02
Applicant: AMAZON TECHNOLOGIES, INC.
Inventor： Imry Kissos , Joel Wilson Brown , Ilia Vitsnudel , Omer Meir , Lior Fritz , Matan Goldman , Eduard Oks
CPC classification number: G16H20/30 , A63B24/0006 , A63B71/0622 , G06T19/20 , G06V20/40 , G06V40/23 , G09B19/003 , A63B2024/0009 , A63B2024/0068 , A63B2024/0096 , A63B2071/0647 , A63B2220/806 , A63B2220/833 , A63B2220/836 , G06T2200/24 , G06T2219/2016
Abstract: To assist a user in the correct performance of an activity, video data is acquired. A pose of the user is determined from the video data and an avatar is generated representing the user in the pose. The pose of the user is compared to one or more other poses representing correct performance of the activity to determine one or more differences that may represent errors by the user. Depending on the activity that is being performed, some errors may be presented to the user during performance of the activity, while other errors may be presented after performance of the activity has ceased. To present an indication of an error, a specific body part or other portion of the avatar that corresponds to a difference between the user's pose and a correct pose may be presented along with an instruction regarding correct performance of the activity.
-
公开(公告)号：US10257542B1
公开(公告)日：2019-04-09
申请号：US14668492
申请日：2015-03-25
Applicant: Amazon Technologies, Inc.
IPC: H04N19/86 , H04N19/136
Abstract: Devices, systems and methods are disclosed for improving color resolution in YUV subsampled signals. Chrominance data may be subsampled using two different techniques and the two different outputs may be interlaced to improve a resulting color resolution as perceived by a viewer. Luminance data may be adjusted in paired frames to improve the perceived color resolution without affecting the perceived luminance values. High edge areas, including high frequency variations in luminance values, may be adaptively desaturated to improve the perceived color resolution of the resulting output.
-
公开(公告)号：US11457804B1
公开(公告)日：2022-10-04
申请号：US16401896
申请日：2019-05-02
Applicant: AMAZON TECHNOLOGIES, INC.
Inventor： Noam Sorek , Ilia Vitsnudel
IPC: A61B3/032 , G06F3/01 , G06T7/70 , G06F40/109
Abstract: Information about changes in vision over time is useful to determine the health of a user. An electronic device has a display that presents visual information to a user. A sensor generates distance data that is used to determine a distance between the user and the display at particular times. Other data may also be acquired that is indicative of whether the user is wearing glasses, tilt of the user's head relative to the display, ambient light level, display brightness, what is being presented on the display such as video content or text content, font size, and so forth. The data is used to determine if the user's vision has changed beyond a threshold amount. If so, an action may be taken, such as providing a recommendation to the user. For example, the user may be advised to consult a health care provider.
-
公开(公告)号：US10419666B1
公开(公告)日：2019-09-17
申请号：US14982736
申请日：2015-12-29
Applicant: Amazon Technologies, Inc.
Inventor： Ilya Vladimirovich Brailovskiy , Ilia Vitsnudel , Paul Berenberg , Noam Sorek
Abstract: Devices, systems and methods are disclosed for generating stitched video data by combining video data from multiple image capture devices. For example, video data from a first image capture device and a second image capture device located near the first image capture device may be combined to generate unique panoramas. The system may determine transitions between the video data based on a focus distance to improve the stitched video data. The system may remove individual objects from first video data by substituting corresponding portions of second image data. The system may determine depth information associated with a first object represented in the video data and may add additional objects in front of or behind the first object, properly scaling and masking the additional object. The system may generate a virtual environment by weighting images from individual image capture devices and the virtual environment may be three dimensional.
-
公开(公告)号：US10298932B1
公开(公告)日：2019-05-21
申请号：US14668436
申请日：2015-03-25
Applicant: Amazon Technologies, Inc.
IPC: H04N19/136 , H04N7/01
Abstract: Devices, systems and methods are disclosed for improving color resolution in YUV subsampled image signals. Chrominance data may be subsampled using two different techniques and the two different outputs may be interlaced to improve a resulting color resolution as perceived by a viewer. Luminance data may be adjusted in paired frames to improve the perceived color resolution without affecting the perceived luminance values. High edge areas, including high frequency variations in luminance values, may be adaptively desaturated to improve the perceived color resolution of the resulting output.
-
-
-
-
-
-
-
-
-
Search Results
11
records
(took 0.016 seconds)
