System and method for monitoring for driver presence and position using a driver facing camera

1. A method for determining a presence of an occupant within a vehicle, comprising:

capturing, via a driver facing camera, video image data, including a plurality of image frames of a field-of-view of the driver facing camera;

defining at least one area-of-interest within the image frames;

determining a foreground pixel count of each image frame of each area-of-interest by counting the number of pixels in the foreground of the image frame;

determining, at each Nth image frame, an occupancy for each area-of-interest based at least in part on the foreground pixel count, the occupancy indicating whether the occupant is present or absent in the respective area-of-interest;

maintaining a history of the occupancy determination for each area-of-interest; and

determining a final status for each area-of-interest based on the respective history of occupancy.

2. The method of claim 1 , further comprising:

determining an edge pixel count of each image frame of each area-of-interest,

wherein the determination of the occupancy is also based on the edge pixel count.

3. The method of claim 2 , wherein determining the edge pixel count is via application of a Sobel operator to the image frame.

4. The method of claim 1 , wherein determining the foreground pixel count is via frame-to-frame differencing.

5. The method of claim 1 , wherein every Nth image frame is from every 5 image frames to every 20 image frames.

6. The method of claim 1 , wherein defining the area-of-interest includes generating an area-of-interest mask, and wherein the foreground pixel count is determined based on a logical AND operation applied to the area-of-interest mask and a foreground pixel identification.

7. The method of claim 1 , wherein defining the area-of-interest includes generating an area-of-interest mask, and wherein the edge pixel count is determined based on a logical AND operation applied to the area-of-interest mask and an edge pixel identification.

8. The method of claim 1 , wherein determining the foreground pixel count of each area-of-interest includes tracking an observed characteristic value of each pixel within each area-of-interest for significant changes over a predetermined period.

9. The method of claim 1 , further comprising:

initiating external indicators and/or vehicle functions based on the final status determination.

10. The method of claim 9 , wherein at least one of the vehicle functions initiated is an anti-rollaway function.

11. The method of claim 9 , wherein the final status of each area-of-interest is determined independently, but wherein the external indicators and/or vehicle functions are initiated based on a combined consideration of the respective final statuses of a plurality of areas-of-interest.

12. The method of claim 11 , wherein at least one of the vehicle functions initiated is an anti-rollaway function.

13. A system for determining a presence of an occupant within a vehicle, comprising:

a driver facing camera configured to capture video image data, including a plurality of image frames of a field-of-view;

a mask module configured to define at least one area-of-interest within the image frames;

a difference module configured to determine a foreground pixel count of each image frame of each area-of-interest by counting the number of pixels in the foreground of the image frame; and

a status module configured to:

determine, at each Nth image frame, an occupancy for each area-of-interest based at least in part on the foreground pixel count, the occupancy indicating whether the occupant is present or absent in the respective area-of-interest,

maintain a history of the occupancy determination for each area-of-interest, and

determine a final status for each area-of-interest based on the respective history of occupancy.

14. The system of claim 13 , further comprising:

an edge extraction module configured to determine an edge pixel count of each image frame of each area-of-interest, wherein the determination of the occupancy is also based on the edge pixel count.

15. The system of claim 14 , wherein determining the edge pixel count is via application of a Sobel operator to the image frame.

16. The system of claim 13 , wherein determining the foreground pixel count is via frame-to-frame differencing.

17. The system of claim 13 , wherein every Nth image frame is from every 5 image frames to every 20 image frames.

18. The system of claim 13 , wherein defining the area-of-interest includes generating an area-of-interest mask, and wherein the foreground pixel count is determined based on a logical AND operation applied to the area-of-interest mask and a foreground pixel identification.

19. The system of claim 13 , wherein defining the area-of-interest includes generating an area-of-interest mask, and wherein the edge pixel count is determined based on a logical AND operation applied to the area-of-interest mask and an edge pixel identification.

20. The system of claim 13 , wherein determining the foreground pixel count of each area-of-interest includes tracking an observed characteristic value of each pixel within each area-of-interest for significant changes over a predetermined period.

21. The system of claim 13 , further comprising:

a controller configured to initiate external indicators and/or vehicle functions based on the final status determination.

22. The system of claim 21 , wherein at least one of the vehicle functions initiated is an anti-rollaway function.

23. The system of claim 21 , wherein the final status of each area-of-interest is determined independently, but wherein the external indicators and/or vehicle functions are initiated based on a combined consideration of the respective final statuses of a plurality of areas-of-interest.

24. The system of claim 23 , wherein at least one of the vehicle functions initiated is an anti-rollaway function.