Apparatus and method for determining tow hitch location

1. A system for determining a location of a tow hitch mounted to a vehicle, the system comprising:

imaging means disposed in relation to the vehicle to output image data corresponding to an image; and

processing means arranged to:

receive the image data,

select a region of the image, wherein the region is a portion of the image,

detect a predetermined shape in the region of the image;

extract a plurality of template areas of image data based on the detected predetermined shape;

extract at least one feature from each of the plurality of template areas;

perform a classification to identify which of the plurality of template areas contains the location of the tow hitch; and

determine an indication of the location of the tow hitch based on the classification.

2. The system of claim 1 , wherein the region of the image is a predetermined region within the image.

3. The system of claim 1 , wherein the predetermined shape is a circle.

4. The system of claim 1 , wherein the processing means is arranged to extract at least one feature from each of the plurality of template areas by determining a distribution of gradients associated with each potential location of the tow hitch within the selected region of the image.

5. The system of claim 1 , wherein the processing means is arranged to detect the predetermined shape by applying a Hough transform to the selected region of the image to identify one or more locations of the predetermined shape, each location corresponding to a respective potential location of the tow hitch.

6. The system of claim 5 , wherein the processing means is further arranged to output a Histogram of Gradients, HOG, associated with each potential location of the tow hitch within the selected region of the image.

7. The system of claim 1 , wherein the processing means is arranged to use a Support Vector Machine classifier to perform the classification.

8. The system of claim 1 , wherein the processing means is further arranged to use a Speeded Up Robust Features (SURF) feature detector.

9. The system of claim 1 , wherein the processing means is further arranged to fit a shape corresponding to the tow hitch to the tow hitch region of the image data to determine the location of the tow hitch within the image.

10. The system of claim 1 , comprising output means arranged to provide the indication of the location of the tow hitch to an occupant of the vehicle.

11. The system of claim 10 , wherein the output means comprises a visual display means and the indication indicative of the location of the tow hitch comprises a representation of at least a portion of the image and a visual indicator indicative of the location of the tow hitch.

12. The system of claim 1 , wherein the processing means is further arranged to output the indication of the location of the tow hitch to an autonomous driving module.

13. The system of claim 1 , wherein the processing means is arranged to select the region of the image based on either or both an expected, approximate, location of the tow hitch and a resolution of the camera.

14. The system of claim 1 , wherein the region is a rectangular region between first and second opposite corner locations in the image.

15. The system of claim 1 , wherein the processing means is further arranged to determine the location of each corner location as a coordinate (x, y) with respect to a datum such as a corner of the image.

16. The system of claim 1 , wherein the processing means is arranged to select the region of the image to be large enough to allow movement of the imaging means either or both during manufacture or use of the vehicle.

17. A controller for a vehicle tow assist system, the controller comprising:

input means for receiving image data corresponding to an image of a region proximal to a vehicle; and

processing means for:

selecting a region of the image, wherein the region is a portion of the image;

detecting a predetermined shape in the region of the image;

extracting a plurality of template areas of image data based on the detected predetermined shape;

extracting at least one feature from each of the plurality of template areas;

performing a classification to identify which of the plurality of template areas contains the location of the tow hitch; and

determining an indication of the location of the tow hitch based on the classification.

18. The controller of claim 17 , further comprising output means for outputting the indication of the location of the tow hitch.

19. A method of determining a location of a tow hitch mounted to a vehicle, the method comprising:

receiving image data corresponding to an image of a region proximal to a vehicle;

selecting a region within the image, wherein the region is a portion of the image;

detecting a predetermined shape in the region within the image;

extracting a plurality of template areas of image data based on the detected predetermined shape;

extracting at least one feature from each of the plurality of template areas;

performing a classification to identify which of the plurality of template areas contains the location of the tow hitch; and

determining an indication of the location of the tow hitch based on the classification.

20. The method of claim 19 , wherein the predetermined shape is a circle.