公开(公告)号：US11995530B2

公开(公告)日：2024-05-28

申请号：US17878724

申请日：2022-08-01

Applicant: Google LLC

Inventor： Aaron Michael Donsbach ,  Christopher Breithaupt ,  Li Zhang ,  Arushan Rajasekaram ,  Navid Shiee

IPC: G06N3/044 ,  G06N3/045 ,  G06N3/048 ,  G06N3/084 ,  H04N23/60 ,  H04N23/611 ,  H04N23/62 ,  H04N23/63

CPC classification number: G06N3/044 ,  G06N3/045 ,  G06N3/084 ,  H04N23/611 ,  H04N23/62 ,  H04N23/632 ,  H04N23/64

Abstract: The present disclosure provides systems and methods that provide feedback to a user of an image capture device that includes an artificial intelligence system that analyzes incoming image frames to, for example, determine whether to automatically capture and store the incoming frames. An example system can also, in the viewfinder portion of a user interface presented on a display, a graphical intelligence feedback indicator in association with a live video stream. The graphical intelligence feedback indicator can graphically indicate, for each of a plurality of image frames as such image frame is presented within the viewfinder portion of the user interface, a respective measure of one or more attributes of the respective scene depicted by the image frame output by the artificial intelligence system.

公开(公告)号：US20180367752A1

公开(公告)日：2018-12-20

申请号：US16109708

申请日：2018-08-22

Applicant: Google LLC

Inventor： Aaron Michael Donsbach ,  Benjamin Vanik ,  Jon Gabriel Clapper ,  Alison Lentz ,  Joshua Denali Lovejoy ,  Robert Douglas Fritz, III ,  Krzysztof Duleba ,  Li Zhang ,  Juston Payne ,  Emily Anne Fortuna ,  Iwona Bialynicka-Birula ,  Blaise Aguera-Arcas ,  Daniel Ramage ,  Benjamin James McMahan ,  Oliver Fritz Lange ,  Jess Holbrook

IPC: H04N5/77 ,  G06K9/66 ,  G06K9/62 ,  H04N5/232 ,  H04N19/426

Abstract: The present disclosure provides an image capture, curation, and editing system that includes a resource-efficient mobile image capture device that continuously captures images. In particular, the present disclosure provides low power frameworks for controlling image sensor mode in a mobile image capture device. On example low power frame work includes a scene analyzer that analyzes a scene depicted by a first image and, based at least in part on such analysis, causes an image sensor control signal to be provided to an image sensor to adjust at least one of the frame rate and the resolution of the image sensor.

公开(公告)号：US20180183997A1

公开(公告)日：2018-06-28

申请号：US15901450

申请日：2018-02-21

Applicant: Google LLC

Inventor： Alexandros Andre Chaaraoui ,  Carlos Hernandez Esteban ,  Li Zhang ,  Steven Maxwell Seitz

IPC: H04N5/232 ,  G03B27/00 ,  G06F3/01

CPC classification number: H04N5/23225 ,  G03B27/00 ,  G06F3/017 ,  H04N5/23238 ,  H04N5/23245

Abstract: Aspects of the disclosure relate to capturing panoramic images using a computing device. For example, the computing device may record a set of video frames and tracking features each including one or more features that appear in two or more video frames of the set of video frames within the set of video frames may be determined. A set of frame-based features based on the displacement of the tracking features between two or more video frames of the set of video frames may be determined by the computing device. A set of historical feature values based on the set of frame-based features may also be determined by the computing device. The computing device may determine then whether a user is attempting to capture a panoramic image based on the set of historical feature values. In response, the computing device may capture a panoramic image.

公开(公告)号：US09936128B2

公开(公告)日：2018-04-03

申请号：US14717492

申请日：2015-05-20

Applicant: Google LLC

Inventor： Alexandros Andre Chaaraoui ,  Carlos Hernandez Esteban ,  Li Zhang ,  Steven Maxwell Seitz

IPC: H04N5/232 ,  G03B27/00 ,  G06F3/01

CPC classification number: H04N5/23225 ,  G03B27/00 ,  G06F3/017 ,  H04N5/23238 ,  H04N5/23245

Abstract: Aspects of the disclosure relate to capturing panoramic images using a computing device. For example, the computing device may record a set of video frames and tracking features each including one or more features that appear in two or more video frames of the set of video frames within the set of video frames may be determined. A set of frame-based features based on the displacement of the tracking features between two or more video frames of the set of video frames may be determined by the computing device. A set of historical feature values based on the set of frame-based features may also be determined by the computing device. The computing device may determine then whether a user is attempting to capture a panoramic image based on the set of historical feature values. In response, the computing device may capture a panoramic image.

公开(公告)号：US20230297852A1

公开(公告)日：2023-09-21

申请号：US18007379

申请日：2021-07-29

Applicant: Google LLC

Inventor： Li Zhang ,  Andrew Gerald Howard ,  Brendan Wesley Jou ,  Yukun Zhu ,  Mingda Zhang ,  Andrey Zhmoginov

IPC: G06N5/022

CPC classification number: G06N5/022

Abstract: Example implementations of the present disclosure combine efficient model design and dynamic inference. With a standalone lightweight model, the unnecessary computation on easy examples is avoided and the information extracted by the lightweight model also guide the synthesis of a specialist network from the basis models. With extensive experiments on ImageNet it is shown that a proposed example BasisNet is particularly effective for image classification and a BasisNet-MV3 achieves 80.3% top-1 accuracy with 290 M MAdds without early termination.

公开(公告)号：US20210248179A1

公开(公告)日：2021-08-12

申请号：US17049452

申请日：2018-09-18

Applicant: Google LLC

Inventor： David Karam ,  Li Zhang ,  Ariel Gilder ,  Yuzo Watanabe ,  Eric Penner ,  Farooq Ahmad ,  Hartwig Adam

IPC: G06F16/583 ,  G06N20/00 ,  G06F16/55 ,  G06F16/535

Abstract: The present disclosure is directed to processing imagery using one or more machine learning (ML) models. In particular, data describing imagery comprising a plurality of different and distinct frames can be received; and based at least in part on one or more ML models and the data describing the imagery, and for each frame of the plurality of different and distinct frames, one or more scores can be determined for the frame. Each score of the score(s) can indicate a determined measure of suitability of the frame with respect to one or more of various different and distinct uses for which the ML model(s) are configured to determine suitability of imagery.

公开(公告)号：US10728489B2

公开(公告)日：2020-07-28

申请号：US16109708

申请日：2018-08-22

Applicant: Google LLC

Inventor： Aaron Michael Donsbach ,  Benjamin Vanik ,  Jon Gabriel Clapper ,  Alison Lentz ,  Joshua Denali Lovejoy ,  Robert Douglas Fritz, III ,  Krzysztof Duleba ,  Li Zhang ,  Juston Payne ,  Emily Anne Fortuna ,  Iwona Bialynicka-Birula ,  Blaise Aguera-Arcas ,  Daniel Ramage ,  Benjamin James McMahan ,  Oliver Fritz Lange ,  Jess Holbrook

IPC: G06K9/66 ,  H04N5/77 ,  G06K9/62 ,  H04N19/426 ,  H04N5/232 ,  G06N3/04 ,  H04N9/82 ,  H04N19/132 ,  H04N19/46 ,  G06K9/46 ,  H04N19/436 ,  H04N19/423 ,  H04N19/85 ,  H04N9/804 ,  G06K9/00 ,  H04N19/136 ,  G06N3/08 ,  G06N5/00

Abstract: The present disclosure provides an image capture, curation, and editing system that includes a resource-efficient mobile image capture device that continuously captures images. In particular, the present disclosure provides low power frameworks for controlling image sensor mode in a mobile image capture device. On example low power frame work includes a scene analyzer that analyzes a scene depicted by a first image and, based at least in part on such analysis, causes an image sensor control signal to be provided to an image sensor to adjust at least one of the frame rate and the resolution of the image sensor.

公开(公告)号：US20250094798A1

公开(公告)日：2025-03-20

申请号：US18727800

申请日：2022-02-03

Applicant: Google LLC

Inventor： Li Zhang ,  Matthew Sharifi ,  David Petrou ,  Blaise Aguera y Arcas

IPC: G06N3/08

Abstract: Systems and methods for partitioning a large model that has been configured to use a model-synthesis approach in which multiple basis models are combined to generate a final output. The present technology provides systems and methods for identifying a device-specific or subject-specific subset of those basis models to be used on a given device, such that it need not store the weight matrices for the entire set of basis models, and may perform inference using only the weight matrices of the identified subset of basis models. In some examples, the subset of basis models used by a given device may be updated based on actual usage and feedback. Likewise, in some examples, the model may be trained in a federated setting in which multiple devices each utilize different subsets of the basis models, and share training signals with a full copy of the model.

公开(公告)号：US20240273340A1

公开(公告)日：2024-08-15

申请号：US18641054

申请日：2024-04-19

Applicant: Google LLC

Inventor： Aaron Michael Donsbach ,  Christopher Breithaupt ,  Li Zhang ,  Arushan Rajasekaram ,  Navid Shiee

IPC: G06N3/044 ,  G06N3/045 ,  G06N3/084 ,  H04N23/60 ,  H04N23/611 ,  H04N23/62 ,  H04N23/63

CPC classification number: G06N3/044 ,  G06N3/045 ,  G06N3/084 ,  H04N23/611 ,  H04N23/62 ,  H04N23/632 ,  H04N23/64

Abstract: The present disclosure provides systems and methods that provide feedback to a user of an image capture device that includes an artificial intelligence system that analyzes incoming image frames to, for example, determine whether to automatically capture and store the incoming frames. An example system can also, in the viewfinder portion of a user interface presented on a display, a graphical intelligence feedback indicator in association with a live video stream. The graphical intelligence feedback indicator can graphically indicate, for each of a plurality of image frames as such image frame is presented within the viewfinder portion of the user interface, a respective measure of one or more attributes of the respective scene depicted by the image frame output by the artificial intelligence system.

公开(公告)号：US11947591B2

公开(公告)日：2024-04-02

申请号：US17049452

申请日：2018-09-18

Applicant: Google LLC

Inventor： David Karam ,  Li Zhang ,  Ariel Gilder ,  Yuzo Watanabe ,  Eric Penner ,  Farooq Ahmad ,  Hartwig Adam

IPC: G06N20/00 ,  G06F16/535 ,  G06F16/55 ,  G06F16/583

CPC classification number: G06F16/583 ,  G06F16/535 ,  G06F16/55 ,  G06N20/00

Abstract: The present disclosure is directed to processing imagery using one or more machine learning (ML) models. In particular, data describing imagery comprising a plurality of different and distinct frames can be received; and based at least in part on one or more ML models and the data describing the imagery, and for each frame of the plurality of different and distinct frames, one or more scores can be determined for the frame. Each score of the score(s) can indicate a determined measure of suitability of the frame with respect to one or more of various different and distinct uses for which the ML model(s) are configured to determine suitability of imagery.