MACHINE LEARNING FOR PHASE DETECTION AUTOFOCUS

    公开(公告)号:US20230379579A1

    公开(公告)日:2023-11-23

    申请号:US17664142

    申请日:2022-05-19

    CPC classification number: H04N5/232122 H04N5/23222 H04N5/2258

    Abstract: This disclosure provides systems, methods, and devices for image capture using an autofocus (AF) algorithm. In a first aspect, a method for autofocus includes receiving first image data of a first scene from a first image sensor of a first camera, the first image data comprising phase shift information; determining a first focal distance for the first scene based on a machine learning algorithm by inputting the phase shift information to the machine learning algorithm; and controlling a focal position of the first camera based on the first focal distance. Other aspects and features are also claimed and described.

    Dynamic field of view compensation for autofocus

    公开(公告)号:US11115600B1

    公开(公告)日:2021-09-07

    申请号:US16900829

    申请日:2020-06-12

    Abstract: An image processing device receives image data from an image frame captured by an image sensor of an image capture device. The image processing device moves a lens of the image capture device while still receiving the image data from the image frame, for instance as part of an autofocus operation. The image processing device determines multiple positions of the lens from the beginning of the movement to the end of the movement based on a lens position sensor, based on differences between the image frame and other consecutive image frames, or based on interpolation. The image processing device performs field of view compensation on the image data by cropping one or more rows of the image data based on the positions of the lens.

    Machine learning for phase detection autofocus

    公开(公告)号:US11843858B1

    公开(公告)日:2023-12-12

    申请号:US17664142

    申请日:2022-05-19

    CPC classification number: H04N23/672 H04N23/45 H04N23/64

    Abstract: This disclosure provides systems, methods, and devices for image capture using an autofocus (AF) algorithm. In a first aspect, a method for autofocus includes receiving first image data of a first scene from a first image sensor of a first camera, the first image data comprising phase shift information; determining a first focal distance for the first scene based on a machine learning algorithm by inputting the phase shift information to the machine learning algorithm; and controlling a focal position of the first camera based on the first focal distance. Other aspects and features are also claimed and described.

Patent Agency Ranking