Abstract: A method for non-invasive operator health monitoring is disclosed. The method may include receiving at least one of one or more images or one or more videos of tracked one or more facial features of a pilot from one or more pilot monitoring devices. The one or more tracked facial features may include at least one of a pilot's eyes, mouth, head posture, forehead, or cheek. The method may include determining at least one of one or more eye tracking parameters, one or more mouth tracking parameters, one or more head tracking parameters, or an emotion of the pilot. The method may include determining a pilot health monitoring value based on at least one of the determined one or more eye tracking parameters, the determined one or more mouth tracking parameters, the one or more head tracking parameters, or the determined emotion of the pilot.

Abstract: A system and method for automated video generation for training machine and deep learning algorithms in aviation environments generates photorealistic digital human characters and an aviation environment according to a desired scenario, including fixtures, free objects, lighting and physics configurations, and camera views. Character actions in the desired scenario are mapped to pose sequences which may be manually generated or transferred from image sequences of human activities, including both main character activities specified by the scenario, characters responding to the main characters, and background character actions. A video automation pipeline animates character actions performed by the digital human characters into video datasets with annotation files incorporating detailed pixel and depth information for each frame. Video datasets may include variant video datasets differentiated from the primary dataset by changes in domain variants (e.g.