-
公开(公告)号：US11610282B2
公开(公告)日：2023-03-21
申请号：US17313221
申请日：2021-05-06
Applicant: Axis AB
Inventor： Viktor Edpalm , Song Yuan , Johan Förberg , Viktors Jakovels
Abstract: A digital camera and a method for aligning digital images comprising: receiving images including first and second images depicting a first and a second region of a scene, the regions being overlapping and displaced along a first direction; aligning the images using a transformation; determining disparity values for an overlap between the images; identifying misalignments by identifying blocks of pixels in the first image having a same position along a second direction and having disparity values exhibiting a variability lower than a first threshold and exhibiting an average higher than a second threshold; adjusting the transformation for the identified blocks of pixels in the first image and their matching blocks of pixels in the second image; and realigning the images using the adjusted transformation.
-
公开(公告)号：US11323620B2
公开(公告)日：2022-05-03
申请号：US17191157
申请日：2021-03-03
Applicant: Axis AB
Inventor： Song Yuan
Abstract: A method for power consumption optimization in a wearable camera comprises: monitoring a bitrate of a video stream captured by the wearable camera. Upon the bitrate being above a first bitrate threshold, activating a movement sensor of the wearable camera. Upon activation of the movement sensor, analyzing whether activation of the movement sensor is beneficial for reducing the bitrate. In case activation of the movement sensor is beneficial for reducing the bitrate, keeping the movement sensor active and performing image stabilization based on movement data from the movement sensor, otherwise, deactivating the movement sensor. Also, a wearable camera is presented.
-
公开(公告)号：US11146817B2
公开(公告)日：2021-10-12
申请号：US16807208
申请日：2020-03-03
Applicant: Axis AB
Inventor： Viktor Edpalm , Song Yuan
IPC: H04N19/597 , H04N19/176 , H04N19/12 , H04N19/182 , H04N19/154
Abstract: A method for encoding, using a block-based video encoding algorithm, a distorted image frame produced via at least one image sensor, comprising: determining a map of maximum pixel block sizes corresponding to the distorted image frame, wherein the map of maximum pixel block sizes is determined based on a spatial resolution distribution corresponding to a distribution of extents of the corresponding FOV, such that for a first portion of the distorted image frame having a first spatial resolution, the maximum pixel block size corresponding to the first portion is set to a first value, and for a second portion of the distorted image frame having a second spatial resolution being lower than the first spatial resolution, the maximum pixel block size corresponding to the second portion is set to a second value being lower than the first value; and encoding, using the block-based video encoding algorithm, the distorted image frame.
-
公开(公告)号：US10972724B2
公开(公告)日：2021-04-06
申请号：US16425569
申请日：2019-05-29
Applicant: Axis AB
Inventor： Song Yuan , Alexander Toresson
IPC: H04N19/159 , H04N19/172 , H04N19/107 , H04N5/232
Abstract: A method, a controller, and a system for encoding a sequence of video frames captured by a camera mounted to a moving object. The method comprises receiving input indicating an amount of movement of the camera, receiving input regarding a predetermined distance, and selecting between intra-coding and inter-coding of the video frames of the sequence based on the amount of movement of the camera and the predetermined distance, such that the camera moves at most the predetermined distance between capturing video frames which are intra-coded.
-
公开(公告)号：US20210092398A1
公开(公告)日：2021-03-25
申请号：US16947654
申请日：2020-08-11
Applicant: Axis AB
Inventor： Viktor Edpalm , Song Yuan
IPC: H04N19/136 , H04N19/593 , H04N19/172 , H04N19/162
Abstract: Methods and apparatus, including computer program products, implementing and using techniques for encoding a video sequence comprising a plurality of image frames, by an encoder are described. An image frame is received from a video stream. An input is received, which indicates one or more regions in the received image frame for which a privacy mask should be applied. The one or more regions are represented by one or more coding units. The image frame is encoded into an output frame, wherein image data in the one or more regions is replaced by intra-predicted coding units with transformed coefficients set to zero, the intra-predicted coding units are obtained from a prediction stage in the encoder.
-
Patent Agency Ranking
公开(公告)号：US10924761B2
公开(公告)日：2021-02-16
申请号：US15848670
申请日：2017-12-20
Applicant: AXIS AB
Inventor： Viktor Edpalm , Song Yuan
IPC: H04N19/593 , H04N19/172 , H04N19/159 , H04N19/17 , H04N19/61 , H04N19/167 , H04N19/105
Abstract: A technique for encoding a privacy masked image comprising a plurality of pixels into an encoded image frame of a video stream is disclosed, The technique includes receiving image data of the image, wherein the image data represents the pixel of the image, grouping the pixels of the image into encoding units, wherein each encoding unit comprises a plurality of neighboring pixels; receiving data defining a privacy mask masking part of the image in the interest of personal integrity, and graphical characteristics of the privacy mask including any one or a combination of constant coloring, smearing, and pixelization, identifying all encoding units having one or more pixels located within the privacy mask, extending the privacy mask to be aligned with the identified encoding units to form a redefined privacy mask covering the identified encoding units, generating a privacy masked image by applying the redefined privacy mask and the received graphical characteristics to the image, and encoding the privacy masked image into the encoded image frame of the video stream.
-
公开(公告)号：US10783646B2
公开(公告)日：2020-09-22
申请号：US16351042
申请日：2019-03-12
Applicant: Axis AB
Inventor： Axel Keskikangas , Song Yuan
Abstract: A method for detecting motion in a video sequence comprising distorted image frames is provided. The method comprises determining (101) a spatial resolution distribution for the distorted image frames; determining (102) a motion detection sensitivity map for the distorted image frames, the motion detection sensitivity map comprising areas having different motion detection sensitivity levels, wherein the motion detection sensitivity map is determined based on the spatial resolution distribution; and detecting (103) motion in the video sequence based on the motion detection sensitivity map. A motion detecting component and a camera including such a component is also disclosed.
-
公开(公告)号：US20190149747A1
公开(公告)日：2019-05-16
申请号：US16186137
申请日：2018-11-09
Applicant: Axis AB
Inventor： Axel Keskikangas , Song Yuan
Abstract: A method for splitting a wide angle view of a scene into a plurality of display views is provided. The wide angle view is captured by a wide angle lens camera. The method comprises detecting, over time, objects in the scene; determining positions of the detected objects; determining one or more areas of interest within the scene based on the determined positions of the objects; and determining splitting boundaries for the plurality of display views in the wide angle view such that the splitting boundaries avoids the one or more areas of interest. A monitoring camera having a wide angle lens is also provided.
-
公开(公告)号：US10049424B2
公开(公告)日：2018-08-14
申请号：US14956499
申请日：2015-12-02
Applicant: Axis AB
Inventor： Song Yuan
IPC: H04N21/2343 , H04N21/24 , H04N21/258 , H04N21/414 , G06T1/20 , H04N21/431 , H04N19/85
Abstract: The present invention relates to the field of processing a video stream, and more particular to the field of post processing of a video stream using shaders. The processing of the video stream is divided between a video stream processing device and a client device.
-
公开(公告)号：US20180176597A1
公开(公告)日：2018-06-21
申请号：US15848670
申请日：2017-12-20
Applicant: AXIS AB
Inventor： Viktor Edpalm , Song Yuan
IPC: H04N19/593 , H04N19/172
CPC classification number: H04N19/593 , H04N19/105 , H04N19/159 , H04N19/167 , H04N19/17 , H04N19/172 , H04N19/61
Abstract: A method for encoding an image comprising a plurality of pixels into an encoded image frame of a video stream, the method comprising: receiving pixel divided image data of the image, wherein the pixel divided image data represents the pixels of the image; grouping the pixels of the image into encoding units, wherein each encoding unit comprises a plurality of neighboring pixels; receiving data defining a privacy mask and graphical characteristics of the privacy mask; identifying all encoding units having one or more pixels located within the privacy mask; extending the privacy mask to be aligned with the identified encoding units, thereby forming a redefined privacy mask covering the identified encoding units; generating a privacy masked image by applying the redefined privacy mask and the received graphical characteristics to the image; and encoding the privacy masked image into the encoded image frame of the video stream.
-
-
-
-
-
-
-
-
-
Search Results
73
records
(took 0.02 seconds)
