System and method for controlling a camera based on processing an image captured by other camera

1. A method for controlling a first camera by estimating the angular deviation between a person gaze direction and a digital camera line of sight, for use with a device including a first digital camera having a first center line of sight and a second digital camera having a second center line of sight with a known vector difference from the first center line of sight, the method comprising the steps of:

capturing an image to an image file by the second digital camera; detecting a human face in the image by using a face detection algorithm;

estimating an angular deviation α between the second center line of sight and an imaginary line from the second camera to the detected human face based on the captured image;

estimating an angular deviation β between the imaginary line from the second camera to the detected face and the human face gaze direction based on the captured image;

estimating an angular deviation φ between the first center line of sight and the human face gaze direction based on the estimated angular deviation α and the estimated angular deviation β; and

initiating, controlling, stopping, or inhibiting an action is response to the value of the estimated angular deviation φ.

2. The method according to claim 1 wherein the step of estimating of the angular deviation α includes estimating a horizontal angular deviation between the second horizontal center line of sight and the horizontally detected human face; and wherein the step of estimating of the angular deviation β includes estimating the horizontal angular deviation between the horizontal line of sight to the detected face and the horizontal human face gaze direction.

3. The method according to claim 1 wherein the step of estimating of the angular deviation α includes estimating a vertical angular deviation between the second vertical center line of sight and the horizontally detected human face; and wherein the step of estimating of the angular deviation β includes estimating the vertical angular deviation between the vertical line of sight to the detected face and the vertical human face gaze direction.

4. The device housed in a single enclosure and comprising in the single enclosure the first and second digital cameras, a memory for storing computer executable instructions, and a processor for executing the instructions, the processor configured by the memory to perform acts comprising the method of claim 1 .

5. The device according to claim 4 wherein the single enclosure is a portable or a hand-held enclosure and the device is battery-operated.

6. The method according to claim 1 wherein the angular deviation α is estimated based on the detected face location in the captured image.

7. The method according to claim 6 wherein the angular deviation α is estimated based on the detected face location deviation from the center of the image.

8. The method according to claim 1 wherein the step of estimating the angular deviation β is based on applying a head pose or gaze direction estimation algorithm on the captured image.

9. The method according to claim 8 wherein the gaze direction estimation algorithm is further based on, or using, eye detection, or eye tracking.

10. The method according to claim 8 wherein the gaze direction estimation algorithm is further based on, or using, facial landmarks detection.

11. The method according to claim 1 wherein the step of estimating the angular deviation β is estimated to be 0°, based on detecting a right ear and a left ear.

12. The method according to claim 1 wherein the step of estimating the angular deviation β is estimated to be 30° when detecting right ear, a left eye, and a right eye, and not detecting a left ear, the angular deviation β is estimated to be 30°.

13. The method according to claim 1 wherein the step of estimating the angular deviation β is based on applying a gaze direction estimation algorithm on the captured image;

wherein the device further comprises a third digital camera having a third center line of sight that is with a known vector difference from to the first center line of sight, the method further comprising the steps of:

capturing an additional image to an additional image file by the third digital camera; and

forming a 3D representation of the detected human face by combining the captured image and the additional captured image; and

wherein the step of estimating the angular deviation β includes analyzing the formed 3D human face representation.

14. The method according to claim 1 wherein the action comprises controlling the first camera.

15. The method according to claim 14 wherein the controlling of the first digital camera includes changing a setting of the first digital camera.

16. The method according to claim 15 wherein the controlling of the first digital camera includes saving an image captured by the first camera in a memory.

17. The method according to claim 1 for use with a maximum threshold value or a minimum threshold value, and wherein the method further comprising the step of respectively comparing the angular deviation φ to the maximum or minimum threshold.

18. The method according to claim 17 further comprising the step of respectively initiating, stopping, controlling, or inhibiting the action if the value of the angular deviation φ is higher than the maximum value or is lower than the minimum value.

19. The method according to claim 18 further comprising the step of respectively initiating, stopping, controlling, or inhibiting the action if the value of the angular deviation φ is higher than the maximum value or is lower than the minimum value for a time interval.

20. The method according to claim 1 wherein the device further includes a visual annunciator comprising a visual signaling component, and wherein the taking an action comprises activating or controlling the visual annunciator.