MOBILEYE VISION TECHNOLOGIES LTD 2020-07-166 Dec 2020 10:54
NAVIGATION BASED ON SENSED LOOKING DIRECTION OF A PEDESTRIAN
The present disclosure relates to systems and methods for host vehicle navigation. Disclosed systems and methods may receive, from a camera, a plurality of images representative of an environment of the host vehicle; analyze the plurality of images to identify at least one pedestrian in the environment of the host vehicle; identify eyes of the at least one pedestrian represented in at least one of the plurality of images; and determine, based on analysis of the at least one of the plurality of images and based on the identification of the eyes of the at least one pedestrian in the at least one of the plurality of images, a looking direction of the at least one pedestrian.
[0387] Activity indicator module 1904 may store instructions (such as computer vision software) which, when executed by processing unit 110, obtains, from at least one host vehicle component associated with an interior of the host vehicle, an indicator of an activity of an occupant of the host vehicle. The at least one component may comprise a camera associated with the interior of the host vehicle, a microphone associated with the interior of the host vehicle, an eye tracking system of the host vehicle, an infotainment system of the host vehicle, or the like.
[0388] For example, activity indicator module 1904 may perform image analysis on captured images of the occupant in order to identify or categorize an activity of the occupant. Similarly, activity indicator module 1904 may categorize audio captured by the microphone in order to categorize an activity of the occupant. For example, softer music may be associated with sleeping while louder music may be associated with passengers who are awake. In another example, activity indicator module 1904 may associate the occupant's voice with an activity of conversing and silence with other activities such as reading. In yet another example, activity indicator module 1904 may associate a looking direction of the occupant's eyes out the window with an activity of looking out the window, a looking direction of the occupant's eyes towards a book, tablet, or the like with an activity of reading, and other looking directions with other activities. In another example, activity indicator module 1904 may associate interactions with an infotainment system as associated with an activity of listening to music, navigating, or the like. Any of the indicators described above may be combined. For example, a combination of soft music from the microphone and a classification of eyes being closed in captured images may result in a determination that the occupant is sleeping. In another example, a combination of a looking direction out the window with silence may result in a determination that the occupant is looking out the window. In any of the embodiments described above, the activity may include drinking, eating, reading, sleeping, looking out of windows, or the like.