公开(公告)号：US12126903B2

公开(公告)日：2024-10-22

申请号：US18364767

申请日：2023-08-03

Applicant: GoPro, Inc.

Inventor： Maxim Karpushin ,  Thomas Derbanne

IPC: H04N23/68 ,  G06T7/215 ,  G06T7/246

CPC classification number: H04N23/683 ,  G06T7/215 ,  G06T7/246 ,  H04N23/6811 ,  H04N23/6812 ,  G06T2207/10016

Abstract: A video including visual content may be captured by an image capture device in motion. Stabilization performance information for the visual content may be determined. The stabilization performance information may characterize an extent to which desired stabilization is able to be performed using the visual content. The stabilization for the visual content may be changed based on the stabilization performance information.

公开(公告)号：US12106553B2

公开(公告)日：2024-10-01

申请号：US17539849

申请日：2021-12-01

Applicant: The Boeing Company

Inventor： Vandan Patel ,  Nick Shadbeh Evans ,  Eric Raymond Muir

IPC: G06V10/82 ,  G06T7/215 ,  G06V10/25 ,  G06V10/26 ,  G06V10/44 ,  G06V10/764 ,  G06V10/77 ,  G06V20/58

CPC classification number: G06V10/82 ,  G06T7/215 ,  G06V10/25 ,  G06V10/26 ,  G06V10/44 ,  G06V10/764 ,  G06V10/7715 ,  G06V20/58

Abstract: A computer-implemented method is provided for detecting a dynamic object in a visual line of sight of an aircraft. The method includes implementing, by a computer system, the following operations: receiving at least two image frames; detecting a horizon within at least one of the at least two image frames; segmenting each of the at least two image frames into at least first and second search regions using the detected horizon, wherein the first search region is defined above the detected horizon in the at least two image frames and the second search region is defined below the horizon in the at least two image frames; determining, across the at least two image frames, a motion vector field within at least one of the first search region or the second search region; and identifying a detection proposal using the determined motion vector field.

公开(公告)号：US20240312053A1

公开(公告)日：2024-09-19

申请号：US18269879

申请日：2021-12-13

Applicant: Sony Group Corporation

Inventor： Natsuko OZAKI

IPC: G06T7/73 ,  G06T7/215

CPC classification number: G06T7/74 ,  G06T7/215 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30196

Abstract: There is provided a reasoning apparatus to estimate positions of predetermined areas of subjects more highly precisely. The reasoning apparatus includes an acquiring section that acquires second image data and a trained model obtained on the basis of a third reference position and a fourth reference position that are obtained by a moving process of moving a first reference position of a first subject captured in first image data and a second reference position of a second subject captured in the first image data away from each other, and a third relative position and a fourth relative position that are obtained on the basis of a first relative position of a predetermined area of the first subject relative to the first reference position, a second relative position of a predetermined area of the second subject relative to the second reference position and the moving process, and a reasoning section that obtains a fifth reference position of a third subject captured in the second image data and a fifth relative position of a predetermined area of the third subject relative to the fifth reference position on the basis of the trained model and the second image data.

公开(公告)号：US20240308505A1

公开(公告)日：2024-09-19

申请号：US18183867

申请日：2023-03-14

Applicant: QUALCOMM Incorporated

Inventor： Thomas Alexander RYDER ,  Muhammed Zeyd COBAN ,  Marta KARCZEWICZ

IPC: B60W30/095 ,  G06T7/215

CPC classification number: B60W30/0953 ,  G06T7/215

Abstract: A device includes one or more processors configured to obtain encoded data associated with one or more motion values. The one or more processors are also configured to obtain conditional input of a compression network, wherein the conditional input is based on one or more first predicted motion values. The one or more processors are further configured to process, using the compression network, the encoded data and the conditional input to generate one or more second predicted motion values.

公开(公告)号：US12056882B2

公开(公告)日：2024-08-06

申请号：US17298685

申请日：2019-11-27

Applicant: Sony Semiconductor Solutions Corporation

Inventor： Yasushi Sato

IPC: G06T7/215 ,  G06T5/20 ,  G06T5/73

CPC classification number: G06T7/215 ,  G06T5/20 ,  G06T5/73 ,  G06T2207/20201

Abstract: Provided is an image processing apparatus which includes a region detection section configured to detect at least one predetermined region from a captured image on the basis of data attached to the captured image, and an image processing section configured to perform noise reduction processing on an image of the predetermined region detected by the region detection section.

公开(公告)号：US20240242484A1

公开(公告)日：2024-07-18

申请号：US18098009

申请日：2023-01-17

Applicant: Palo Alto Research Center Incorporated

Inventor： Robert Roy Price ,  Yan-Ming Chiou

IPC: G06V10/774 ,  G06T7/215 ,  G06V10/26 ,  G06V10/56 ,  G06V10/77

CPC classification number: G06V10/774 ,  G06T7/215 ,  G06V10/273 ,  G06V10/56 ,  G06V10/7715 ,  G06T2207/20081

Abstract: An augmented data set is generated by combining chroma key substitutions for background and occlusion augmentations for foreground to enable training of object detectors or action recognition that transfers to multiple environments and is robust to occlusion due to other objects or human hands.

公开(公告)号：US20240221183A1

公开(公告)日：2024-07-04

申请号：US18387176

申请日：2023-11-06

Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor： Yuta MORI

IPC: G06T7/215 ,  E01F9/559 ,  G06V20/52

CPC classification number: G06T7/215 ,  E01F9/559 ,  G06V20/52 ,  G06T2207/30232 ,  G06T2207/30241

Abstract: A mobile object included in an image of an infrastructure camera is recognized. A supporting display for supporting a movement of a mobile object is output from a pavement lighting device based on the recognition information. When the recognition information includes recognition information of first and second mobile objects, a relative speed of the second mobile object in a movement direction of the first mobile object and a distance between these mobile objects are calculated based on the recognition information. When the relative speed is equal to or greater than a predetermined speed and the distance is equal to or less than a predetermined distance, proximity notification information for notifying the first mobile object of the approach of the second mobile object is generated. When the proximity notification information is generated, the supporting display corresponding to the proximity notification information is output from the pavement lighting device.

公开(公告)号：US12026896B2

公开(公告)日：2024-07-02

申请号：US17751795

申请日：2022-05-24

Applicant: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD.

Inventor： Jingjing Zhuge ,  Guangyao Ni ,  Hui Yang

IPC: G06T7/246 ,  G06T7/215 ,  G06V10/82 ,  G06V20/40 ,  G06V40/20 ,  H04N21/4223 ,  H04N21/431 ,  H04N21/44 ,  H04N21/4788 ,  H04N21/81

CPC classification number: G06T7/246 ,  G06T7/215 ,  G06V20/46 ,  G06V40/28 ,  G06V10/82 ,  H04N21/4223 ,  H04N21/4312 ,  H04N21/44008 ,  H04N21/4788 ,  H04N21/8146

Abstract: Disclosed in embodiments of the present disclosure are a method and apparatus for displaying an object in a video, and an electronic device and a computer readable storage medium. The method for displaying an object in a video comprises: obtaining and displaying a video acquired by a photographing element; and in response to detecting that a first target action appears in the video, displaying a generation process of the target object in the video on the basis of the display position of the first target action in the video, wherein the generation process of the target object comprises: the target object appears at the display position and changes from small to large.

公开(公告)号：US20240202940A1

公开(公告)日：2024-06-20

申请号：US18084606

申请日：2022-12-20

Applicant: Adobe Inc.

Inventor： Chang Xiao ,  Ryan Rossi ,  Enyu Cai

IPC: G06T7/246 ,  G06T7/215 ,  G06T7/73 ,  G06T15/20

CPC classification number: G06T7/248 ,  G06T7/215 ,  G06T7/74 ,  G06T15/205 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30244 ,  G06T2210/56

Abstract: Certain aspects and features of this disclosure relate to providing a hybrid approach for camera pose estimation using a deep learning-based image matcher and a match refinement procedure. The image matcher takes an image pair as an input and estimates coarse point-to-point feature matches between the two images. The coarse point-to-point feature matches can be filtered based on a stability threshold to produce high-stability point-to-point matches. A perspective-n-point (PnP) camera pose for each frame of video, including one or more added digital visual elements can be computed using the high-stability matches and video frames can be rendered, each using its computed camera pose.

公开(公告)号：US12008807B2

公开(公告)日：2024-06-11

申请号：US17220832

申请日：2021-04-01

Applicant: Sarcos Corp.

Inventor： Fraser M. Smith

IPC: G06V20/17 ,  G06T7/11 ,  G06T7/215 ,  G06V10/62

CPC classification number: G06V20/17 ,  G06T7/11 ,  G06T7/215 ,  G06V10/62 ,  G06T2207/30181 ,  G06T2207/30248

Abstract: Systems and methods are disclosed for scanning a predetermined area of an aerial landscape with one or more cameras for an airborne target and capturing a plurality of images of the airborne target with the one or more cameras, the one or more cameras in communication with a processor. Microscopic temporal variations between the plurality of images of the airborne target are amplified including a change in the geometry of a two-dimensional image of the airborne target.