Systems and Methods for Autonomous Vehicle Sensor Calibration and Validation
AssigneeArgo AI, LLC
InventorsParul Kothari, Hatem Alismail
Life of this patent
Estimating the term…
Abstract
Methods and systems for determining whether a camera of an autonomous vehicle (AV) is calibrated are disclosed. The method includes determining a relative positional range for a calibration target with respect to the AV, capturing a plurality of images of the calibration target, using the camera when the calibration target and the AV are positioned within the relative positional range, measuring a camera-based calibration factor and a motion-based validation factor based on the plurality of images for generating a confidence score, and generating a signal indicating that the camera is not calibrated when the confidence score is below a threshold.
Claims20
A method of determining whether a camera of an autonomous vehicle (AV) is calibrated, comprising:
- determining, for a calibration target, a relative positional range with respect to the AV, the relative positional range comprising a plurality of locations and a plurality of orientations of the calibration target relative to the AV;
- capturing, using the camera, a plurality of images of the calibration target when the calibration target and the AV are positioned within the relative positional range;
- measuring, based on the plurality of images, a camera-based calibration factor and a motion-based validation factor;
- using the camera-based calibration factor and the motion-based validation factor to generate a confidence score;
- and
- in response to the confidence score being below a threshold, generating a signal indicating that the camera is not calibrated.
A system of determining whether a camera of an autonomous vehicle (AV) is calibrated, the system comprising:
- a processor;
- and
- a non-transitory computer-readable medium comprising programming instructions that when executed by the processor will cause the processor to:
- determine, for a calibration target, a relative positional range with respect to the AV, the relative positional range comprising a plurality of locations and a plurality of orientations of the calibration target relative to the AV,
- capture, using the camera, a plurality of images of the calibration target when the calibration target and the AV are positioned within the relative positional range,
- measure, based on the plurality of images, a camera-based calibration factor and a motion-based validation factor,
- use the camera-based calibration factor and the motion-based validation factor to generate a confidence score, and
- in response to the confidence score being below a threshold, generate a signal indicating that the camera is not calibrated.
A computer program product comprising a memory and programming instructions that are configured to cause a processor to:
- determine, for a calibration target, a relative positional range with respect to an autonomous vehicle (AV), the relative positional range comprising a plurality of locations and a plurality of orientations of the calibration target relative to the AV,
- capture, using a camera, a plurality of images of the calibration target when the calibration target and the AV are positioned within the relative positional range,
- measure, based on the plurality of images, a camera-based calibration factor and a motion-based validation factor,
- use the camera-based calibration factor and the motion-based validation factor to generate a confidence score, and
- in response to the confidence score being below a threshold, generate a signal indicating that the camera is not calibrated.
Dependencies are inferred from the claim text.