System and method for latency reduction in an optical imaging system

A computer-implemented method of latency reduction in a digital holography optical imaging system, the method comprising:

• receiving an incoming light field;
• generating a reconstructed image and estimated phase error based on the received incoming light field, wherein the reconstructed image and estimated phase error are generated by a digital holographic model-based iterative reconstruction (DH-MBIR) method defined by an initial condition, and wherein the reconstructed image and estimated phase error are defined by a computation latency of the DH-MBIR method;
• applying the reconstructed image and estimated phase error generated by the DH-MBIR method to a first adaptive predictor;
• generating, with the first adaptive predictor, a revised initial condition for the DH-MBIR method;
• applying the reconstructed image and estimated phase error generated by the DH-MBIR method to a second adaptive predictor;
• and
• generating, with the second adaptive predictor, a predicted future image and predicted future phase error associated with a future time.

An optical imaging system comprising:

• a laser configured to emit light;
• a focal plane array configured to receive an incoming light field including reflected light from the laser;
• an interfering light source configured to apply an interfering light field to the focal plane array;
• and
• at least one processor configured to:
• generate an image based on the incoming light field and the interfering light field at the focal plane array;
• generate a sequence of phase errors based on the image;
• generate at least one training parameter based on the sequence of phase errors;
• train a neural network to provide at least one revised training parameter using the sequence of phase errors, a time delay, and the at least one training parameter;
• and
• predict a fixture phase error for a future image based on the revised training parameter.