System and method for autonomous valet parking using plenoptic cameras
Exemplary embodiments provide systems and methods for autonomously valet parking a vehicle based on images obtained from a plurality of plenoptic (light field) cameras. According to one embodiment, an autonomous valet parking system comprises a plenoptic camera configured to: obtain an image external to a vehicle, and for the image, generate a depth map including location information for an object in the image; and a controller configured to: using the depth map, generate an occupancy map indicating whether each of a plurality of regions surrounding the vehicle is occupied; and using the occupancy map, control the vehicle to navigate to a desired parking space.
1. An autonomous parking system comprising:
a plenoptic camera configured to generate a depth map based on the image external to the vehicle, the depth map including location information for object in the image; and
a controller configured to:
using the depth map, generate an occupancy map indicating occupied regions in a plurality of concentric sets of regions surrounding the vehicle; and
using the occupancy map, control the vehicle to navigate to a desired parking space.
2. The system of claim 1 , wherein the controller is configured to identify the desired parking space by analyzing the occupancy map to determine if the occupancy map includes unoccupied regions indicative of an available parking space.
3. The system of claim 2 , wherein the controller is configured to designate the available parking space as the desired parking space.
4. The system of claim 1 , wherein the desired parking space is a designated parking space having a location stored in a memory of the controller.
5. The system of claim 1 , wherein the location information includes a distance from a point on a surface of the object to the plenoptic camera.
6. The system of claim 1 , wherein the controller is configured to determine a location of the vehicle in a parking area by comparing any objects in the image to a plurality of objects included in a parking area map of a parking area.
7. The system of claim 6 , wherein the controller is configured to, using the occupancy map, the location of the vehicle, and the parking area map, navigate the vehicle to a location within the parking area where parking spaces are located.
8. The system of claim 7 , wherein the controller is configured to identify the desired parking space by analyzing the occupancy map to determine if the occupancy map includes unoccupied regions indicative of an available parking space.
9. The system of claim 8 , wherein the controller is configured to designate the available parking space as the desired parking space.
10. The system of claim 1 , wherein each of the regions in the plurality of concentric sets of regions are defined to have a length of ten centimeters.
11. An autonomous parking method comprising:
generating, by a plenoptic camera, a depth map based on the image external to the vehicle, the depth map including location information for object in the image;
using the depth map, generating an occupancy map indicating occupied regions in a plurality of concentric sets of regions surrounding the vehicle; and
using the occupancy map, controlling, by the controller, the vehicle to navigate to a desired parking space.
12. The method of claim 11 , which includes identifying, by the controller, the desired parking space by analyzing the occupancy map to determine if the occupancy map includes unoccupied regions indicative of an available parking space.
13. The method of claim 12 , which includes designating, by the controller, the available parking space as the desired parking space.
14. The method of claim 11 , wherein the desired parking space is a designated parking space having a location stored in a memory of the controller.
15. The method of claim 11 , wherein the location information includes a distance from a point on a surface of the object to the plenoptic camera.
16. The method of claim 11 , which includes determining, by the controller, a location of the vehicle in a parking area by comparing any objects in the image to a plurality of objects included in a parking area map of a parking area.
17. The method of claim 16 , which includes navigating, by the controller and using the occupancy map, the location of the vehicle, and the parking area map, the vehicle to a location within the parking area where parking spaces are located.
18. The method of claim 17 , which includes identifying, by the controller, the desired parking space by analyzing the occupancy map to determine if the includes unoccupied regions indicative of an available parking space.
19. The method of claim 18 , which includes designating, by the controller, the available parking space as the desired parking space.
20. The method of claim 11 , wherein each of the regions in the plurality of concentric sets of regions are defined to have a length of ten centimeters.