SENSOR FUSION BASED PERCEPTUALLY ENHANCED SURROUND VIEW

    公开(公告)号:US20210092327A1

    公开(公告)日:2021-03-25

    申请号:US17115378

    申请日:2020-12-08

    Abstract: Techniques including obtaining a first location of a vehicle, the vehicle having two or more cameras disposed about the vehicle, each camera associated with a physical camera pose, capturing, by a first camera, a first image of a first area in a first field of view, associating the first image with the first location of the vehicle when the first image was captured, moving the vehicle in a direction so that the first area is in an expected second field of view of a second camera, wherein the second camera is not capturing images, obtaining a second location of the vehicle, determining a temporal camera pose based on a first physical camera pose, a second physical camera pose, and the second location of the vehicle, and rendering a view of the first area from the expected second field of view of the second camera based on the first image.

    ALTERNATING FRAME PROCESSING OPERATION WITH PREDICTED FRAME COMPARISONS FOR HIGH SAFETY LEVEL USE

    公开(公告)号:US20220060740A1

    公开(公告)日:2022-02-24

    申请号:US17520795

    申请日:2021-11-08

    Abstract: Frames from an image stream or streams are processed by independently operating digital signal processors (DSPs), with only frame checking microprocessors operating in a lockstep mode. In one example, two DSP are operating on alternate frames. Each DSP processes the frames and produces prediction values for the next frame. The lockstep microprocessors develop their own next frame prediction. The lockstep processors compare issued frames and previously developed predicted frames for consistency. If the predictions are close enough, the issued frame passes the test. The lockstep processors then compare the issued frame to the preceding two frames for a similar consistency check. If the prior frames are also close enough, the issued frame is acceptable. In another example, hardware checkers are provided to compare the present frame with a larger number of prior frames. The hardware checkers provide comparison results to the lockstep processors to compare against allowable variation limits.

    ALTERNATING FRAME PROCESSING OPERATION WITH PREDICTED FRAME COMPARISONS FOR HIGH SAFETY LEVEL USE

    公开(公告)号:US20230111755A1

    公开(公告)日:2023-04-13

    申请号:US18079237

    申请日:2022-12-12

    Abstract: Frames from an image stream or streams are processed by independently operating digital signal processors (DSPs), with only frame checking microprocessors operating in a lockstep mode. In one example, two DSP are operating on alternate frames. Each DSP processes the frames and produces prediction values for the next frame. The lockstep microprocessors develop their own next frame prediction. The lockstep processors compare issued frames and previously developed predicted frames for consistency. If the predictions are close enough, the issued frame passes the test. The lockstep processors then compare the issued frame to the preceding two frames for a similar consistency check. If the prior frames are also close enough, the issued frame is acceptable. In another example, hardware checkers are provided to compare the present frame with a larger number of prior frames. The hardware checkers provide comparison results to the lockstep processors to compare against allowable variation limits.

    RECONFIGURABLE EXECUTION OF MACHINE LEARNING NETWORKS

    公开(公告)号:US20230064481A1

    公开(公告)日:2023-03-02

    申请号:US17463341

    申请日:2021-08-31

    Abstract: An electronic device, comprising one or more processors, wherein the one or more processors are configured to execute instructions causing the one or more processors to: receive a machine learning (ML) model and execution information associated with the ML model, wherein the execution information including first execution data indicating how to execute the ML model optimized based on a first performance criterion, and second execution data execution data indicating how to execute the ML model optimized based on a second performance criteria, the second performance criterion different from the first performance criteria; execute the ML model based on the first execution data; determine to execute the ML model based on the second execution data; and execute the ML model based on the second execution data.

    ALTERNATING FRAME PROCESSING OPERATION WITH PREDICTED FRAME COMPARISONS FOR HIGH SAFETY LEVEL USE

    公开(公告)号:US20210203979A1

    公开(公告)日:2021-07-01

    申请号:US16866647

    申请日:2020-05-05

    Abstract: Frames from an image stream or streams are processed by independently operating digital signal processors (DSPs), with only frame checking microprocessors operating in a lockstep mode. In one example, two DSP are operating on alternate frames. Each DSP processes the frames and produces prediction values for the next frame. The lockstep microprocessors develop their own next frame prediction. The lockstep processors compare issued frames and previously developed predicted frames for consistency. If the predictions are close enough, the issued frame passes the test. The lockstep processors then compare the issued frame to the preceding two frames for a similar consistency check. If the prior frames are also close enough, the issued frame is acceptable. In another example, hardware checkers are provided to compare the present frame with a larger number of prior frames. The hardware checkers provide comparison results to the lockstep processors to compare against allowable variation limits.

    SENSOR FUSION BASED PERCEPTUALLY ENHANCED SURROUND VIEW

    公开(公告)号:US20210075959A1

    公开(公告)日:2021-03-11

    申请号:US16690906

    申请日:2019-11-21

    Abstract: Techniques including obtaining a first location of a vehicle, the vehicle having one or more cameras disposed about the vehicle, and wherein each camera is associated with a physical camera pose indicating where each camera is located with respect to the vehicle, capturing, by a first camera, a first image of a first area, associating the first image with the first location of the vehicle when the first image was captured, moving the vehicle in a direction so that the first area is no longer within a field of view of the first camera, obtaining a second location of the vehicle, determining a temporal camera pose based on the physical camera pose of the first camera and the second location of the vehicle, and rendering a view of the first area based on the temporal camera pose and the first image.

Patent Agency Ranking