Visual Inertial Odometry Health Fitting

A system comprising:

• an image capture device;
• memory;
• and
• one or more programmable control devices operable to interact with the image capture device and the memory, and to perform operations comprising:
• receiving one or more visual inertial odometry (VIO) feature measurements associated with a set of image frames from a VIO system, wherein the VIO feature measurements are based on the VIO system's processing of the set of image frames to determine position, orientation, or health information;
• generating a plurality of feature models to estimate health values for the VIO system, wherein each feature model includes at least one feature model parameter;
• determining a plurality of feature health values with the feature models based on the VIO feature measurements;
• comparing the feature health values with ground truth health scores associated with the set of image frames to determine one or more errors between the feature health values and the ground truth health scores;
• and
• updating the feature model parameters for one or more of the feature model based on the error.

A method comprising:

• obtaining, using an electronic device, one or more visual inertial odometry (VIO) feature measurements associated with a set of image frames from a VIO system, wherein the VIO feature measurements are based on the VIO system's processing of the set of image frames to determine position, orientation, or both types of information;
• generating, using the electronic device, a plurality of feature models to estimate health values for the VIO system, wherein each feature model includes at least one feature model parameter;
• determining, using the electronic device, a plurality of feature health values with the feature models based on the VIO feature measurements;
• comparing, using the electronic device, the feature health values with ground truth health scores associated with the set of image frames to determine one or more errors between the feature health values and the ground truth health scores;
• and
• updating, using the electronic device, the feature model parameters for one or more of the feature models based on the errors.