Abstract: An exemplary method includes a gesture recognition system determining, based on imagery of a user while the user touchlessly interacts with a user interface of a computer system, a configuration of a plurality of landmarks associated with the user and comparing the configuration of the plurality of landmarks to defined landmark configurations associated with a plurality of defined gestures. Each of the plurality of defined gestures may be associated with a different user input enterable by way of the user interface of the computer system. The method may further include the gesture recognition system selecting, based on the comparing of the configuration of the plurality of landmarks to the defined landmark configurations associated with the plurality of defined gestures, a defined gesture included in the plurality of defined gestures, and directing the computer system to enter a user input that is associated with the defined gesture.

Abstract: A user device may receive an image of a user, and may process the image, with a model, to identify a face of the user and key markers of the face. The user device my process the face and the key markers, with the model, to identify features of the face, and may calculate a z-index representing a distance between the face and a display. The user device may calculate left and right face rotation along an x-axis of the display, and may calculate up and down face rotation along a y-axis of the display, based on the features. The user device may calculate an x-position and a y-position of a cursor on the display based on the left and right face rotation, the up and down face rotation, and the z-index, and may provide the x-position and the y-position of the cursor to the display.

Abstract: In some implementations, an information tracking device may provide a graphical user interface (GUI) associated with providing contextual assistance to a user. The GUI may include a viewpoint region within a display area of the GUI. The information tracking device may track a content position that is associated with a position of content that is positioned within the viewpoint region. The information tracking device may identify a set of elements that is positioned within the viewpoint region, a set of user interactions associated with the set of elements that is positioned within the viewpoint region, and/or a time period that the content that is positioned within the viewpoint region remains positioned within the viewpoint region. The information tracking device may perform an action related to providing the contextual assistance based on at least one of the set of elements, the set of user interactions, and/or the time period.

Abstract: An exemplary method includes a gesture recognition system determining, based on imagery of a user while the user touchlessly interacts with a user interface of a computer system, a configuration of a plurality of landmarks associated with the user and comparing the configuration of the plurality of landmarks to defined landmark configurations associated with a plurality of defined gestures. Each of the plurality of defined gestures may be associated with a different user input enterable by way of the user interface of the computer system. The method may further include the gesture recognition system selecting, based on the comparing of the configuration of the plurality of landmarks to the defined landmark configurations associated with the plurality of defined gestures, a defined gesture included in the plurality of defined gestures, and directing the computer system to enter a user input that is associated with the defined gesture.

Abstract: One or more computing devices, systems, and/or methods for tracking user interaction with objects based upon eye gazing movements are provided. A canvas is populated with grids corresponding to locations of objects and is populated with an eye cursor positioned to track a gaze of a user. A plurality of image frames captured by a camera are evaluated to track interaction of users with the objects. For an image frame, a midpoint between eyes of a user are identified based upon facial landmarks of the user. A current position of the eye cursor is set within the canvas based upon the midpoint. In response to detecting that the eye cursor intersects a first grid in the canvas, the user is identified as interacting with a first object associated with the first grid.