Automatic parameter adjustment for scanning event cameras

    公开(公告)号:US12148185B2

    公开(公告)日:2024-11-19

    申请号:US17865794

    申请日:2022-07-15

    Abstract: Embodiments are directed to parameter adjustment for sensors. A calibration model and a calibration profile for a sensor may be provided. Calibration parameters associated with the sensor may be determined based on the calibration profile. The sensor may be configured to use a value of the calibration parameter based on the calibration profile. Trajectories may be generated based on a stream of events from the sensor. Metrics associated with the sensor events or the trajectories may be determined. If a metric value may be outside of a control range, further actions may be iteratively performed, including: modifying the value of the calibration parameter based on the calibration model; configuring the sensor to use the modified value of the calibration parameter; redetermining the metrics based on additional trajectories; if the metric is within a control range, the iteration may be terminated and the calibration profile may be updated.

    MULTI-SENSOR SUPERRESOLUTION SCANNING AND CAPTURE SYSTEM

    公开(公告)号:US20230060421A1

    公开(公告)日:2023-03-02

    申请号:US17895489

    申请日:2022-08-25

    Abstract: Embodiments are directed to multi-sensor superresolution scanning and capture system. A sensing system may be employed to scan a plurality of paths across objects using beams such that the sensing system includes event sensors and image sensors and such that the image sensors are a higher resolution than the event sensors. The event sensors may be employed to provide events based on detection of the beams that are reflected by the objects. The image sensors may be employed to provide images based on the reflected the beams. Enhanced trajectories may be generated based on a plurality of first trajectories and a plurality of second trajectories such that the plurality of the first trajectories are based on the events and the plurality of paths and such that the plurality of second trajectories are based on the images and the plurality of paths.

    AUTOMATIC PARAMETER ADJUSTMENT FOR SCANNING EVENT CAMERAS

    公开(公告)号:US20230015889A1

    公开(公告)日:2023-01-19

    申请号:US17865794

    申请日:2022-07-15

    Abstract: Embodiments are directed to parameter adjustment for sensors. A calibration model and a calibration profile for a sensor may be provided. Calibration parameters associated with the sensor may be determined based on the calibration profile. The sensor may be configured to use a value of the calibration parameter based on the calibration profile. Trajectories may be generated based on a stream of events from the sensor. Metrics associated with the sensor events or the trajectories may be determined. If a metric value may be outside of a control range, further actions may be iteratively performed, including: modifying the value of the calibration parameter based on the calibration model; configuring the sensor to use the modified value of the calibration parameter; redetermining the metrics based on additional trajectories; if the metric is within a control range, the iteration may be terminated and the calibration profile may be updated.

    Dynamic calibration of 3D acquisition systems

    公开(公告)号:US11704835B2

    公开(公告)日:2023-07-18

    申请号:US17876333

    申请日:2022-07-28

    CPC classification number: G06T7/80

    Abstract: Embodiments are directed to a sensing system that employs beams to scan paths across an object such that sensors may the beams reflected by the scanned object. Events may be provided based on the detected signals and the paths such that each event may be associated with a sensor and event metrics. Crossing points for each sensor may be determined based on where the paths intersect the scanned object such that events associated with each sensor are associated with the crossing points for each sensor. Each crossing point of each sensor may be compared to each correspondent crossing point of each other sensor. Actual crossing points may be determined based on the comparison and the crossing points for each sensor. Position information for each sensor may be determined based on the actual crossing points.

    PERCEIVING OBJECTS BASED ON SENSING SURFACES AND SENSING SURFACE MOTION

    公开(公告)号:US20220187461A1

    公开(公告)日:2022-06-16

    申请号:US17551054

    申请日:2021-12-14

    Abstract: Embodiments are directed to perceiving surfaces and objects. Trajectories may be generated based on a continuous stream of sensor events such that each trajectory may be a parametric representation of a curve segment. The trajectories may be employed to determine the surfaces. The trajectories may be provided to a modeling engine to execute one or more actions based on the trajectories and the surfaces. In response to changes to the surfaces, the trajectories may be updated based on the continuous stream of sensor events and one or more additional actions may be executed based on the updated trajectories and the changed surfaces. Changes to the surfaces may include a position change, an orientation change, a motion change, a deformation of the one or more surfaces, or the like. Shapes that correspond to the surfaces may be determined based on characteristics of the surfaces or the trajectories.

    Dynamic calibration of 3D acquisition systems

    公开(公告)号:US11887340B2

    公开(公告)日:2024-01-30

    申请号:US18222780

    申请日:2023-07-17

    CPC classification number: G06T7/80

    Abstract: Embodiments are directed to a sensing system that employs beams to scan paths across an object such that sensors may the beams reflected by the scanned object. Events may be provided based on the detected signals and the paths such that each event may be associated with a sensor and event metrics. Crossing points for each sensor may be determined based on where the paths intersect the scanned object such that events associated with each sensor are associated with the crossing points for each sensor. Each crossing point of each sensor may be compared to each correspondent crossing point of each other sensor. actual crossing points may be determined based on the comparison and the crossing points for each sensor. Position information for each sensor may be determined based on the actual crossing points.

    DYNAMIC CALIBRATION OF 3D ACQUISITION SYSTEMS

    公开(公告)号:US20230360268A1

    公开(公告)日:2023-11-09

    申请号:US18222780

    申请日:2023-07-17

    CPC classification number: G06T7/80

    Abstract: Embodiments are directed to a sensing system that employs beams to scan paths across an object such that sensors may the beams reflected by the scanned object. Events may be provided based on the detected signals and the paths such that each event may be associated with a sensor and event metrics. Crossing points for each sensor may be determined based on where the paths intersect the scanned object such that events associated with each sensor are associated with the crossing points for each sensor. Each crossing point of each sensor may be compared to each correspondent crossing point of each other sensor. actual crossing points may be determined based on the comparison and the crossing points for each sensor. Position information for each sensor may be determined based on the actual crossing points.

    DYNAMIC CALIBRATION OF 3D ACQUISITION SYSTEMS

    公开(公告)号:US20230034733A1

    公开(公告)日:2023-02-02

    申请号:US17876333

    申请日:2022-07-28

    Abstract: Embodiments are directed to a sensing system that employs beams to scan paths across an object such that sensors may the beams reflected by the scanned object. Events may be provided based on the detected signals and the paths such that each event may be associated with a sensor and event metrics. Crossing points for each sensor may be determined based on where the paths intersect the scanned object such that events associated with each sensor are associated with the crossing points for each sensor. Each crossing point of each sensor may be compared to each correspondent crossing point of each other sensor. Actual crossing points may be determined based on the comparison and the crossing points for each sensor. Position information for each sensor may be determined based on the actual crossing points.

Patent Agency Ranking