Certain aspects of an apparatus and method for gesture recognition using a two Dimensional (2D) imaging device may include capturing a first image of a hand in a first position, capturing a second image of the hand in a second position, generating an image mask for indicating the movement of the arm from the first position to the second position, determining an elbow position corresponding to the hand based on the image mask and estimating the change in depth of the hand from the first position to the second position based on the determined elbow position.