公开(公告)号：US20220335620A1

公开(公告)日：2022-10-20

申请号：US17230875

申请日：2021-04-14

Applicant: Logitech Europe S.A.

Inventor： Oleg OSTAP ,  Henry LEVAK ,  Miguel Angel MAESTRE TRUEBA ,  Viktor SAKHARCHUK ,  Yaroslav Vasilovich TERESHCHENKO ,  Ihor OKHRIMENKO

IPC: G06T7/194 ,  H04N7/15 ,  G06T7/174 ,  G06T7/11 ,  H04L29/06

Abstract: Embodiments of the present disclosure generally relate to livestreaming methods and systems, and more particularly to whiteboard presentation systems that can be used in a livestreaming or video conferencing environment. In some embodiments, the whiteboard presentation system is configured to perform one or more processing operations, such as capture images on a whiteboard, perform image processing routines on the captured images, and transmit processed images as a video feed to one or more remote users, such as people or locations attending a video conference. The image processing routines can include one or more operations such as image denoising, contrast enhancement, color reconstruction, segmentation of a presenter, and image reconstruction.

公开(公告)号：US20240031529A1

公开(公告)日：2024-01-25

申请号：US17870724

申请日：2022-07-21

Applicant: Logitech Europe S.A.

Inventor： Joseph Yao-Hua CHU ,  Kristopher Glenn PERRY ,  Yu LOH ,  Fu Han CHAO ,  Oleg OSTAP ,  Richard John CAMPBELL ,  Anurag BANSAL ,  Miguel Angel MAESTRE TRUEBA

IPC: H04N7/15

CPC classification number: H04N7/15

Abstract: A system and method for providing video conferencing are described herein. Original video streams from one or more cameras are sampled to form downscaled versions of the video stream. The downscaled version is analyzed to find regions of interest and generate metadata describing aspects of the regions of interest, including a region that includes a preferred speaker and the best view of each participant present together in the video conference. Cropping instructions are generated from the metadata, and portions of the original video stream are removed to form a set of presentation views for each participant, including the preferred speaker. The set of presentation views is stitched together to form a composite display for each participant viewing the stream remotely.

公开(公告)号：US20250008055A1

公开(公告)日：2025-01-02

申请号：US18821784

申请日：2024-08-30

Applicant: Logitech Europe S.A.

Inventor： Joseph Yao-Hua CHU ,  Kristopher Glenn PERRY ,  Yu LOH ,  Fu Han CHAO ,  Oleg OSTAP ,  Richard John CAMPBELL ,  Anurag BANSAL ,  Miguel Angel MAESTRE TRUEBA

IPC: H04N7/15 ,  H04N7/14

Abstract: A system and method for providing video conferencing are described herein. Original video streams from one or more cameras are sampled to form downscaled versions of the video stream. The downscaled version is analyzed to find regions of interest and generate metadata describing aspects of the regions of interest, including a region that includes a preferred speaker and the best view of each participant present together in the video conference. Cropping instructions are generated from the metadata, and portions of the original video stream are removed to form a set of presentation views for each participant, including the preferred speaker. The set of presentation views is stitched together to form a composite display for each participant viewing the stream remotely.

公开(公告)号：US20240054655A1

公开(公告)日：2024-02-15

申请号：US18383358

申请日：2023-10-24

Applicant: Logitech Europe S.A.

Inventor： Oleg OSTAP ,  Henry LEVAK ,  Miguel Angel MAESTRE TRUEBA ,  Viktor SAKHARCHUK ,  Yaroslav Vasilovich TERESHCHENKO ,  Ihor OKHRIMENKO

IPC: G06T7/194 ,  H04N7/15 ,  G06T7/11 ,  H04L65/403 ,  G06T7/174

CPC classification number: G06T7/194 ,  H04N7/15 ,  G06T7/11 ,  H04L65/4046 ,  G06T7/174 ,  G06T2207/10016

Abstract: Embodiments of the present disclosure generally relate to livestreaming methods and systems, and more particularly to whiteboard presentation systems that can be used in a livestreaming or video conferencing environment. In some embodiments, the whiteboard presentation system is configured to perform one or more processing operations, such as capture images on a whiteboard, perform image processing routines on the captured images, and transmit processed images as a video feed to one or more remote users, such as people or locations attending a video conference. The image processing routines can include one or more operations such as image denoising, contrast enhancement, color reconstruction, segmentation of a presenter, and image reconstruction.

公开(公告)号：US20240422285A1

公开(公告)日：2024-12-19

申请号：US18430404

申请日：2024-02-01

Applicant: Logitech Europe S.A.

Inventor： Oleg OSTAP ,  Henry LEVAK ,  Kostiantyn VERHUN ,  Ihor DUTCHAK ,  Sergii NAUMOV ,  Pawel WROBEL ,  Miguel Angel MAESTRE TRUEBA ,  Anurag BANSAL ,  Volodymyr OSTAP ,  Kristopher Glenn PERRY

IPC: H04N5/278 ,  G06V20/40 ,  H04N5/262

Abstract: In one or more embodiments a computer implemented method includes generating, by a sensor, a video stream that comprises a series of frames that include a plurality of objects positioned within an environment, determining the objects captured within at least one frame of the video stream, determining one or more croppings for each of the objects in the at least one frame, determining a ranking of the one or more croppings based on a determined total combined loss value for each the one or more croppings, determining each subtiling combination for each of the one or more croppings, each subtiling combination comprising at least one subtile that includes at least one object; determining a total subtiling penalty value (TSPV) for each subtiling combination, and determining a preferred subtiled combination based on the total combined loss value of each the one or more croppings and the TSPV of each subtiling combination.

公开(公告)号：US20240169698A1

公开(公告)日：2024-05-23

申请号：US17993710

申请日：2022-11-23

Applicant: Logitech Europe S.A.

Inventor： Anurag BANSAL ,  Oleg OSTAP ,  Miguel Angel MAESTRE TRUEBA ,  Kristopher Glenn PERRY

IPC: G06V10/774 ,  G06V10/82 ,  G06V40/10

CPC classification number: G06V10/774 ,  G06V10/82 ,  G06V40/10

Abstract: A method of training a machine learning model includes training a primary part of a composite neural network to identify a primary segment of objects in a training image, freezing the primary part of the composite neural network after training the primary part of the composite neural network, and after freezing the primary part of the composite neural network, training, using activations of the primary part of the composite neural network, a secondary part of the composite neural network to identify a first subsegment of objects or a feature of the first subsegment of objects in the training image. The first subsegment of objects is a subset of the primary segment of objects.