Method, system and computer program product ofr eye gaze direction estimation

The computer-implemented method for eye gaze direction estimation described in the present disclosure intends to solve the shortcomings of prior-art methods. The method of the present disclosure can effectively extend its applicability to different environmental conditions. The considered entities (such as person's face, targets if any, and imaging device) are reconstructed in a common virtual 3D space, which is used to estimate where the person is looking at, without necessarily requiring calibration data, e.g. any initialization procedures.

The method of the present disclosure estimates the direction of eye gaze of a user, from an image of the user taken by an imaging device (such as a camera). The image is a monocular image captured by a monocular imaging device, meaning that the image only provides basic information, such as RGB or greyscale values and resolution.