Systems and methods for validating camera calibration in real-time

A camera calibration system, comprising:

• a processor;
• and
• a memory that contains programming instructions that are configured to instruct the processor to:
• use a plurality of image frames captured by a camera of an autonomous vehicle (AV) and LIDAR point clouds captured by a LIDAR system of the AV to calculate an AV pose calibration metric for the AV,
• measure a distance metric between a three-dimensional (3D) bounding box around an object and a two-dimensional (2D) bounding box in an image captured by the camera,
• use the AV pose calibration metric and the distance calibration metric 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 non-transitory computer-readable medium that stores instructions that are configured to, when executed by a computing device, cause the computing device to:

• use a plurality of image frames captured by a camera of an AV and LIDAR point clouds captured by a LIDAR system of the AV to calculate an AV pose calibration metric for the AV;
• measure a distance metric between a three-dimensional (3D) bounding box around an object and a two-dimensional (2D) bounding box in an image captured by the camera;
• use the AV pose calibration metric and the distance calibration metric 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.