Rendering augmented reality based on foreground object

摘要

A mobile device detects a moveable foreground object in captured images, e.g., a series of video frames without depth information. The object may be one or more of the user's fingers. The object may be detected by warping one of a captured image of a scene that includes the object and a reference image of the scene without the object so they have the same view and comparing the captured image and the reference image after warping. A mask may be used to segment the object from the captured image. Pixels are detected in the extracted image of the object and the pixels are used to detect the point of interest on the foreground object. The object may then be tracked in subsequent images. Augmentations may be rendered and interacted with or temporal gestures may be detected and desired actions performed accordingly.

主权项

1. A method comprising:
capturing an image of a scene with a foreground object that is not attached to the scene, the foreground object including a point of interest that is a distinct physical aspect, wherein the foreground object is at least one of a finger of a user or a pointer and the point of interest is a tip of the at least one of the finger of the user or the pointer; warping at least one of the image and a reference image of the scene that does not include the foreground object so the image and the reference image have a same view; comparing the image to the reference image after warping to detect pixels that belong to the point of interest on the foreground object; detecting the point of interest on the foreground object using the detected pixels; displaying the image on a display; and rendering an augmentation on the display over the image based on the point of interest.