Clear path detection using segmentation-based method

• US 8,670,592 B2
• Filed: 10/19/2009
• Issued: 03/11/2014
• 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 LLC (General Motors Company)
• Inventors: Zhang, Wende
• Primary Examiner(s): Hung, Yubin
• Application Number:
  US12/581,742
• Publication Number:
  US 20100098297A1
• Time in Patent Office: 1,604 Days
• Field of Search: 382/100, 382/104, 382217-221, 382/228, 382/108, 700/259, 701/223, 701300-302, 701/23, 701/28, 348/113, 348/116
• US Class Current: 382/104
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• 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 by segmenting an image generated by a camera device located upon the vehicle includes monitoring the image, analyzing the image with a plurality of analysis methods to segment a region of the image that cannot represent the clear path of travel from a region of the image that can represent the clear path of travel, defining the clear path of travel based upon the analyzing, and utilizing the clear path of travel to navigate the vehicle.

Claims

1. Method for detecting a clear path of travel for a vehicle by segmenting an image generated by a camera device located upon the vehicle, the method comprising:

monitoring the image;

analyzing the image with a plurality of analysis methods, each analysis method

segmenting a respective region of the image that cannot represent the clear path of travel

defining the clear path of travel based upon

subtracting each respective region of the image that cannot represent the clear path of travel from the image,

identifying one or more remaining regions after each respective region of the image that cannot represent the clear path of travel has been subtracted, and

identifying, through geometric analysis, the clear path of travel corresponding only to ones of the remaining regions that comprise a parallelogram-based shape indicative of either one of a current lane of travel and a neighboring lane of travel; and

utilizing the clear path of travel to navigate the vehicle.

2. The method of claim 1, wherein analyzing the image comprises utilizing:

a motion analysis between a plurality of sequential images to identify a region of the image that cannot be the clear path;

a texture analysis of the image to identify a region of the image that cannot be the clear path;

a color analysis of the image to identify a region of the image that cannot be the clear path; and

a geometric analysis of the image to identify a region of the image that cannot be the clear path.

3. The method of claim 2, wherein the motion analysis identifying the region of the image that cannot be a clear path comprises utilizing image subtraction to identify a region of the image that is not stationary.

4. The method of claim 2, wherein the texture analysis identifying the region of the image that cannot be a clear path comprises utilizing a texture rich method to identify features in the image.

5. The method of claim 2, wherein the texture analysis identifying the region of the image that cannot be a clear path comprises utilizing a textureless method to identify properties of different regions in the image.

6. The method of claim 2, wherein the color analysis identifying the region of the image that cannot be a clear path comprises identifying a region in the image that includes a color that cannot be a road surface.

7. The method of claim 2, wherein the geometric analysis identifying the region of the image that cannot be a clear path comprises identifying a region in the image with a shape not supporting transit of the vehicle therethrough.

8. The method of claim 2, wherein the geometric analysis identifying the region of the image that cannot be a clear path comprises identifying a region in the image indicating a surface height difference not supporting transit of the vehicle thereacross.

9. The method of claim 1, wherein analyzing the image comprises:

utilizing an analysis method selected from the group consisting of

a motion analysis between a plurality of sequential images to identify a region of the image that cannot be the clear path,

a texture analysis of the image to identify a region of the image that cannot be the clear path,

a color analysis of the image to identify a region of the image that cannot be the clear path, and

a geometric analysis of the image to identify a region of the image that cannot be the clear path; and

utilizing an additional analysis method selected from the group consisting of

the motion analysis,

the texture analysis,

the color analysis,

the geometric analysis,

a radar analysis of an operating environment of the vehicle to identify a region of the image that cannot be the clear path,

a LIDAR analysis of an operating environment of the vehicle to identify a region of the image that cannot be the clear path,

a vehicle to vehicle communication describing an operating environment of the vehicle to identify a region of the image that cannot be the clear path, and

a vehicle to infrastructure communication describing an operating environment of the vehicle to identify a region of the image that cannot be the clear path.

10. The method of claim 1, wherein analyzing the image comprises:

utilizing an analysis method selected from the group consisting of

histogram thresholding segmentation,

ostu-segmentation,

region growth segmentation,

watershed method segmentation,

K-mean clustering segmentation,

ISODATA segmentation,

graph based segmentation in grid-graph space, and

graph based segmentation in feature space.

11. Method for detecting a clear path of travel for a vehicle by segmenting an image generated by a camera device located upon the vehicle, the method comprising:

monitoring the image;

pre-processing the image, comprising analyzing the image with a plurality of analysis methods, each analysis method segmenting a respective region of the image that cannot represent the clear path of travel;

analyzing the image through clear path detection analysis based upon the pre-processing to determine a clear path of travel within the image, comprising;

subtracting each respective region of the image that cannot represent the clear path of travel from the image,

identifying one or more remaining regions after each respective region of the image that cannot represent the clear path of travel has been subtracted, and

identifying, through geometric analysis, the clear path of travel corresponding only to ones of the remaining regions that comprise a parallelogram-based shape indicative of either one of a current lane of travel and a neighboring lane of travel; and

utilizing the clear path of travel to navigate the vehicle.

12. The method of claim 11, wherein identifying one or more remaining regions comprises utilizing a patch-based analysis comprising utilizing a patch configuration arranging patches to the image based upon the pre-processing to cover a likely road surface.

13. The method of claim 11, wherein identifying one or more remaining regions comprises utilizing a pixel-based analysis, comprising:

identifying a plurality of pixels in the image, each pixel expressed as a function of a plurality of color intensity values;

comparing each pixel with surrounding pixels; and

identifying interest points based on the comparing to identify a likely road surface.

14. The method of claim 11, wherein identifying one or more remaining regions comprises utilizing an example-based analysis, comprising:

matching the image to a stored bank of sample images; and

approximating a likely cleared path from the matched sample images.