METHOD FOR DETECTING A CLEAR PATH THROUGH TOPOGRAPHICAL VARIATION ANALYSIS

• US 20100098290A1
• 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 8,428,305 B2
• Time in Patent Office: Days
• US Class Current: 382/100
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 30/00 Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
• 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

Abstract

A method for detecting a clear path of travel for a vehicle wherein the detecting includes a fusion of a plurality of analyses including monitoring an image from a camera device includes analyzing the image through clear path detection analysis to determine a clear path of travel within the image, analyzing an area in front of the vehicle utilizing a topographical variation analysis to determine a flat surface upon which the vehicle can travel, combining the clear path of travel and the determined flat surface to describe an enhanced clear path of travel, and utilizing the enhanced clear path of travel to navigate the vehicle.

Claims

1. Method for detecting a clear path of travel for a vehicle, the detecting comprising a fusion of a plurality of analyses, the method comprising:

monitoring an image from a camera device;

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

analyzing an area in front of the vehicle utilizing a topographical variation analysis to determine a flat surface upon which the vehicle can travel;

combining the clear path of travel and the determined flat surface to describe an enhanced clear path of travel; and

utilizing the enhanced clear path of travel to navigate the vehicle.

2. The method of claim 1, wherein analyzing the area in front of the vehicle comprises utilizing ground plane estimation analysis.

3. The method of claim 2, wherein utilizing ground plane estimation analysis comprises utilizing a plurality of images to estimate heights of visible features in front of the vehicle based upon relative movement of features between the plurality of images.

4. The method of claim 2, wherein utilizing ground plane estimation analysis comprises utilizing a LIDAR device to determine a ground plane estimate in front of the vehicle.

5. The method of claim 1, wherein analyzing the area in front of the vehicle comprises utilizing snow elevation change analysis.

6. The method of claim 5, wherein the snow elevation change analysis comprises analyzing an image based upon a frequency of pixel change to estimate the flat surface.

7. The method of claim 6, wherein analyzing the image based upon the frequency of pixel change to estimate the flat surface comprises analyzing a change in pixel intensity.

8. The method of claim 6, wherein analyzing the image based upon the frequency of pixel change to estimate the flat surface comprises analyzing a change in pixel color.

9. The method of claim 6, wherein analyzing the image based upon the frequency of pixel change to estimate the flat surface comprises identifying a boundary to the flat surface based upon identifying an area of large pixel change in excess of a threshold.

10. The method of claim 9, wherein analyzing the image based upon the frequency of pixel change to estimate the flat surface further comprises identifying the flat surface based upon identifying an area adjacent to the boundary of moderate pixel change less than the threshold and greater than a lower threshold.

11. The method of claim 6, wherein analyzing the image based upon the frequency of pixel change to estimate the flat surface comprises identifying boundaries upon both sides of the flat surface based upon identifying areas of large pixel change in excess of a threshold.

12. The method of claim 11, wherein analyzing the image based upon the frequency of pixel change to estimate the flat surface further comprises identifying the flat surface based upon identifying an area between the boundaries of moderate pixel change less than the threshold and greater than a lower threshold.

13. The method of claim 1, wherein analyzing the image through clear path detection analysis comprises utilizing an analysis selected from the group consisting of a patch-based analysis, a pixel-based analysis, a segmentation-based analysis, and an example-based analysis.

14. The method of claim 1, wherein analyzing the image through clear path detection analysis comprises utilizing a fusion of analyses selected from the group consisting of a patch-based analysis, a pixel-based analysis, a segmentation-based analysis, and an example-based analysis.

15. The method of claim 1, further comprising iteratively analyzing the area in front of the vehicle utilizing the topographical variation analysis to build confidence in the flat surface.

16. The method of claim 1, wherein combining the clear path of travel and the determined flat surface to describe the enhanced clear path of travel comprises utilizing as the enhanced clear path only an area contained by both the clear path of travel and the determined flat surface.

17. The method of claim 1, wherein combining the clear path of travel and the determined flat surface further describes an enhanced topographical variation analysis;

and

utilizing the enhanced topographical variation analysis to navigate the vehicle.

18. The method of claim 1, wherein the topographical variation analysis comprises ground plane estimation and snow elevation detection.

19. A system for detecting a clear path of travel for a vehicle, the detecting comprising a fusion of a plurality of analyses, the system comprising:

a camera device; and

a processing module

monitor images from the camera device, 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

monitoring data describing topography in front of the vehicle,

analyzing the data describing the topography in front of the vehicle,

analyzing the clear path and the analysis of the data describing the topography in front of the vehicle,

modifying the clear path based upon the analysis of the clear path and the analysis of the data describing the topography in front of the vehicle, and

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

20. The system of claim 19, further comprising an autonomous steering system, wherein the autonomous steering system utilizes the navigation aid from the processing module.