Hand pointing estimation for human computer interaction

摘要

Hand pointing has been an intuitive gesture for human interaction with computers. A hand pointing estimation system is provided, based on two regular cameras, which includes hand region detection, hand finger estimation, two views' feature detection, and 3D pointing direction estimation. The technique may employ a polar coordinate system to represent the hand region, and tests show a good result in terms of the robustness to hand orientation variation. To estimate the pointing direction, Active Appearance Models are employed to detect and track, e.g., 14 feature points along the hand contour from a top view and a side view. Combining two views of the hand features, the 3D pointing direction is estimated.

主权项

1. A method for determining a finger pointing target, comprising:
receiving a plurality of images comprising a sequence of images over time, including images acquired from different perspectives representing a hand having a finger with a finger pointing direction; tracking a plurality of landmarks on the hand comprising at least two visible landmarks of the finger having the finger pointing direction, a center of the hand, and a position of a wrist proximate to the hand, in a series of images, the respective landmarks being derived from common characteristics of hands from a plurality of different people; determining a best fit for visible landmarks of the hand in each of the series of images to an active appearance model; inferring a three dimensional position of each visible landmark in the series of images; determining the finger pointing directional vector of the finger based on the inferred three dimensional position of each visible landmark in the series of images; and determining a finger pointing gesture based on at least a change in the determined directional vector over time.