CLEAR PATH DETECTION THROUGH ROAD MODELING

• US 20100098295A1
• Filed: 10/19/2009
• Published: 04/22/2010
• Est. Priority Date: 04/24/2008
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations Incorporated (Motors Liquidation Co. GUC Trust)
• Inventors: Naik, Sanjeev M., Zhang, Wende
• Granted Patent: US 8,699,754 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: G08G 1/165 for passive traffic, e.g. including static obstacles, trees
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

A method for detecting a clear path of travel for a vehicle including fusion of clear path detection by image analysis and road geometry data describing road geometry includes monitoring an image from a camera device on the vehicle, analyzing the image through clear path detection analysis to determine a clear path of travel within the image, monitoring the road geometry data, analyzing the road geometry data to determine an impact of the data to the clear path, modifying the clear path based upon the analysis of the road geometry data, and utilizing the clear path in navigation of the vehicle.

Claims

1. Method for detecting a clear path of travel for a vehicle including fusion of clear path detection by image analysis and road geometry data describing road geometry, the method comprising:

monitoring an image from a camera device on the vehicle;

analyzing the image through clear path detection analysis to determine a clear path of travel within the image;

monitoring the road geometry data;

analyzing the road geometry data to determine an impact of the data to the clear path;

modifying the clear path based upon the analysis of the road geometry data; and

utilizing the clear path in navigation of the vehicle.

2. The method of claim 1, wherein the analyzing the road geometry data to determine the impact of the data to the clear path comprises detecting lane markers of a current road being traveled upon.

3. The method of claim 2, wherein monitoring the road geometry data comprises monitoring the image from the camera device.

4. The method of claim 3, wherein detecting lane markers of the current road comprises:

applying lighting normalization to the road geometry data to generate normalized road geometry data;

convolving the normalized road geometry data with an edge detection filter for generating an edge-based filter response;

convolving the normalized road geometry data with a line detection filter for generating a line-based filter response;

selecting candidate lane markers in response to the edge-based filter response and the line-based filter response; and

applying a transformation technique to the candidate lane markers for identifying lane markings.

5. The method of claim 4, further comprising applying a false alarm mitigation analysis for verifying whether the identified lane markers are lane markers, wherein the false alarm mitigation analysis comprises:

determining a length of the identified lane markers;

comparing the length to a predetermined length; and

determining that the identified lane markers are lane markers in response to the length being greater than the predetermined length, otherwise determining that the identified lane markers are not lane markers.

6. The method of claim 4, further comprising applying a false alarm mitigation analysis for verifying whether the identified lane markers are lane marker, wherein the false alarm mitigation analysis comprises:

determining a distance between a first identified lane marker and a second identified lane marker;

comparing the distance to a predetermined width, the predetermined width being representative of at least the width of a lane of a road; and

determining the first lane marker and the second lane marker to be lane markers based upon the width being less than the predetermined width, otherwise determining that the first lane marker and second lane marker are not lane markers.

7. The method of claim 6, wherein determining the first lane marker and the second lane marker to be lane markers is further based upon determining the first lane marker and the second lane marker to be parallel to one another, otherwise determining that the first lane marker and second lane marker are not lane markers.

8. The method of claim 4, wherein the detecting lane markers of the current road is performed in real time.

9. The method of claim 4, wherein the road geometry data is segmented into a plurality of straight lines oriented at different angles representing curvatures of potential lane markers in the vehicle road.

10. The method of claim 9, wherein the edge detection filter includes a plurality of oriented edge-based filters, wherein each oriented edge-based filter is applied to each segmented straight line.

11. The method of claim 9, wherein the line detection filter includes a plurality of oriented line-based filters, wherein each oriented line-based filter is applied to each respective segmented straight line.

12. The method of claim 2, wherein monitoring the road geometry data comprises monitoring return data from a LIDAR system.

13. The method of claim 1, wherein analyzing the road geometry data to determine the impact of the data to the clear path comprises detecting a road-edge of a current road being traveled upon.

14. The method of claim 13, wherein detecting the road-edge of the current road comprises:

monitoring the image from the camera device, the image comprising a plurality of pixels;

utilizing a texture-rich analysis to analyze the pixels; and

identifying the road-edge based upon patterns of pixels indicating the road-edge.

15. The method of claim 13, wherein detecting the road-edge of the current road comprises:

monitoring the image from the camera device; and

utilizing a texture-less analysis to analyze the image comprising

filtering the image to separate portions of the image upon which a road-edge can be estimated from other portions of the image that do not indicate a potential road-edge, and

determining the road-edge based upon the filtering.

16. The method of claim 13, wherein monitoring the road geometry data comprises monitoring return data from a LIDAR system.

17. Method for determining an enhanced clear path of travel for a vehicle utilizing analysis of a plurality of images generated by a camera device located upon the vehicle, the method comprising:

monitoring images from the camera device;

analyzing the images from the camera device comprising

determining through camera-based clear path analysis a clear path upon which a potential road surface can be estimated from other portions of the image that do not indicate a potential road surface,

determining a road model describing road geometry, said road geometry comprising

detecting lane markers, and

detecting road-edge,

analyzing the road model and the clear path;

augmenting the road model and the clear path to determine an enhanced clear path; and

utilizing the enhanced clear path in navigation of the vehicle.

18. A system for detecting a clear path of travel for a vehicle utilizing analysis of a plurality of images from a camera device located upon the vehicle, the system comprising:

the camera device; and

a processing module

monitoring the images, and

analyzing the images comprising

determining a clear path of travel from other portions of the image that do not indicate a clear path of travel, and

determining a road model based upon the analysis,

analyzing the clear path and the road model,

modifying the clear path based upon the analysis of the clear path and the road model, and

aiding navigation of the vehicle based upon the modified clear path.

19. The system of claim 18, further comprising an autonomous steering system and a speed control device, wherein the autonomous steering system and speed control device are operative based upon the analyzing the images from the camera system.