System and method to detect a gaze at an object by utilizing an image sensor

A system to detect a gaze at an object by utilizing an image sensor comprising:

• a processing subsystem hosted on a server and configured to control bidirectional communications among a plurality of modules comprising:
• a detection module operatively coupled to an integrated database, wherein the detection module is configured to:
• detect at least one face of a person from one or more images received from the image sensor associated with the object by a face detection technique, wherein the person is located in a field of view of the image sensor:
• identify a gender of the person based on a convolution neural network based technique;
• locate two outer canthal points of the at least one face detected by a key point detection technique;
• estimate a pitch angle and a yaw angle of a head of the person based on at least one of a relative position of the head with respect to the image sensor and an orientation of the head with respect to the image sensor;
• a depth estimator module operatively coupled to the detection module, wherein the depth estimator module is configured to estimate a distance of the person from the image sensor based on the gender identified and the distance between the two outer canthal points located;
• a height estimator module operatively coupled to the depth estimator module, wherein the height estimator module is configured to:
• estimate a height of the person by adding a dimension of a body portion of the person visible in the field of view of the image sensor to a distance between a first predefined point located on the body portion of the person and a ground level when the person is partially visible in the field of view of the image sensor, wherein the first predefined point is coinciding with a bottom line of the field of view of the image sensor;
• estimate the height of the person by subtracting a first distance from the dimension of the body portion of the person visible in the field of view of the image sensor when the person is located within the field of view of the image sensor at a second predefined point located in the ground level,
• wherein the second predefined point is located at a second distance from a third predefined point located in the ground level, wherein the third predefined point is coinciding with the bottom line of the field of view of the image sensor,
• wherein the first distance comprises a perpendicular distance between the ground level and a point of intersection of a vertical axis of the person and the bottom line of the image sensor;
• a horizontal position estimator module operatively coupled to the height estimator module, wherein the horizontal position estimator module is configured to estimate a relative position of the person with respect to at least one of a right edge of the field of view of the image sensor and a left edge of the field of view of the image sensor;
• a computing module operatively coupled to the horizontal position estimator module, wherein the computing module is configured to compute a range of pitch angle and a range of yaw angle based on the distance of the person from the image sensor estimated, the height of the person estimated, the relative position of the person estimated, length of the object, and width of the object;
• and
• a recognizing module configured to recognize the gaze of the person when the pitch angle and the yaw angle of the head of the person estimated falls within the range of pitch angle and the range of yaw angle computed, thereby detecting the gaze of the person by employing the image sensor.