# US 2009/0268946 A1 · Vehicle clear path detection

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2009/0268946 A1
- Document ID: US20090268946A1
- Status: Published application
- Kind: A1
- Application number: 12/108,581
- Filed: 2008-04-24
- Published: 2009-10-29
- Earliest claimed: 2008-04-24
- Assignees: GM Global Technology Operations LLC
- Inventors: Wende Zhang; Mark J. Wolski
- Web page: https://patentgrep.com/patent/US20090268946A1

## CPC

- G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method for vehicle clear path detection using a camera includes imaging a ground area in front of the vehicle with the camera to produce a ground image and analyzing the ground image to formulate a clear path free of objects limiting travel of the vehicle.

## Claims

### Claim 1

A method for vehicle clear path detection using a camera comprising:
imaging a ground area in front of said vehicle with said camera to produce a ground image; and
analyzing said ground image to formulate a clear path free of objects limiting travel of said vehicle including
iteratively identifying a component patch of said ground image,
extracting a feature from said component patch, and
classifying said component patch based upon said feature.

### Claim 2 (depends on 1)

The method of claim 1, wherein extracting a feature comprises feature recognition based on filtering said component patch.

### Claim 3 (depends on 1)

The method of claim 1, wherein classifying comprises:
determining a patch clear path likelihood describing a fractional confidence that said feature is not an object limiting travel of said vehicle;
comparing said patch clear path likelihood to a threshold clear path confidence;
designating said component patch as clear if said patch clear path likelihood is greater than said threshold clear path confidence; and
designating said component patch as not clear if said patch clear path likelihood is not greater than said threshold clear path confidence.

### Claim 4 (depends on 3)

The method of claim 3, wherein determining a patch clear path likelihood comprises:
utilizing a trained classifier database to analogize said feature to trained models; and
assigning a clear path weight to said feature.

### Claim 5 (depends on 3)

The method of claim 3, wherein said threshold clear path confidence is substantially 0.5.

### Claim 6 (depends on 1)

The method of claim 1, wherein identifying said component patch comprises identifying potential objects with a radar imaging system.

### Claim 7 (depends on 1)

The method of claim 1, wherein identifying said component patch comprises:
imaging a second ground area in front of said vehicle to produce a second ground image;
comparing said second ground image to said ground image; and
defining a component patch based on said comparison.

### Claim 8 (depends on 7)

The method of claim 7, wherein comparing said second ground image to said ground image comprises:
referencing said second ground image to said ground image;
generating an image difference by absolute image intensity difference; and
focusing upon an area of said image difference displaying a change in image intensity.

### Claim 9 (depends on 7)

The method of claim 7, wherein comparing said second ground image to said ground image comprises:
referencing said second ground image to said ground image;
generating an image difference comprising a vehicle motion compensated image difference; and
focusing upon an area of said image difference displaying a change in perspective characteristics.

### Claim 10

A method for vehicle clear path detection using a camera comprising:
imaging a first ground area in front of the vehicle with the camera to produce a first ground image;
imaging a second ground area in front of the vehicle with the camera to produce a second ground image; and
analyzing said first and second ground images to formulate a clear path free of objects limiting travel of said vehicle including
identifying a component patch of said first ground image corresponding to an identified potential object,
comparing said second ground image to said first ground image through vehicle motion compensated image differences,
generating a clear path likelihood and a detected object likelihood based on said comparison,
classifying said patch as clear if said clear path likelihood is greater than said detected object likelihood, and
classifying said patch as not clear if said clear path likelihood is not greater than said detected object likelihood.

### Claim 11

An apparatus for vehicle clear path detection comprising:
a camera configured to generate a pixelated image; and
a control module analyzing said pixelated image and generating a clear path output by
iteratively identifying a component patch of said pixelated image,
extracting a feature from said patch, and
classifying said patch based upon said feature.

### Claim 12 (depends on 11)

The apparatus of claim 11, further comprising:
a radar imaging device generating data corresponding to an object in front of said vehicle; and
wherein said control module identifies said component patch on the basis of said data.

### Claim 13 (depends on 11)

The apparatus of claim 11, wherein said control module extracts said feature from said patch by applying feature recognition based on filtering said patch.

### Claim 14 (depends on 11)

The apparatus of claim 11, wherein said control module classifies said patch by
comparing said feature to a trained classifier,
assigning a clear path likelihood to said patch based on said comparison,
designating said patch as clear if said clear path likelihood is greater than a threshold confidence, and
designating said patch as not clear if said clear path likelihood is not greater than a threshold confidence.

### Claim 15 (depends on 11)

The apparatus of claim 11, further comprising:
said camera configured to generate a second pixelated image; and
wherein said control module
compares said pixelated image to said second pixelated image by applying an absolute image intensity difference comparison,
identifies within said comparison a potential object as any area displaying change, and
utilizes said potential object to identify said component patch.

### Claim 16 (depends on 11)

The apparatus of claim 11, further comprising:
said camera configured to generate a second pixelated image; and
wherein said control module
compares said pixelated image to said second pixelated image by applying a vehicle motion compensated image comparison,
identifies within said comparison a potential object as any area displaying change, and
utilizes said potential object to identify said component patch.
