Algorithm to extend detecting range for AVM stop line detection

Patent metadata

Field	Value
Publication number	US-10318824-B2
Application number	US-201514803894-A
Country	US
Kind code	B2
Filing date	Jul 20, 2015
Priority date	Jul 23, 2014
Publication date	Jun 11, 2019
Grant date	Jun 11, 2019

Abstract

A system and method on a vehicle for providing extended detection range of a stop line on a roadway. The system and method includes a front view camera on the vehicle that provides images of the roadway in front of the vehicle and a controller that receives images from the front view camera. The controller is programmed to extract an upper portion of a front view image that is remapped onto an extended bird's eye view image such that the detection range of the stop line is detected.

First claim

What is claimed is:

1. A system on a vehicle that provides extended detection range of a stop line on a roadway, said system comprising:
a front view camera on the vehicle that provides a front view image of the roadway in front of the vehicle; and
a controller that is programmed to:
receive the front view image from the front view camera;
map a region of the front view image into an original bird's eye view;
detect lane markers in the original bird's eye view;
calculate a pixel intensity reference value from the detected lane markers;
extract an upper region of the front view image;
extract white line pixels from the upper region using the pixel intensity reference value;
remap the white line pixels onto an extended bird's eye view according to a camera calibration look up table;
determine a position of a stop line candidate using the white line pixels via a binarization method; and
track the position of the stop line candidate in the extended bird's eye view in subsequent extracted images.

2. The system according to claim 1 further comprising using a predetermined safe value as the reference value if the land markers are not detected in the images from the front view camera.

3. The system according to claim 1 wherein a position of the stop line is predicted using the stop line candidate position that is tracked in the following extracted images.

4. The system according to claim 1 wherein the controller is further programmed to detect an extracted peak from the extracted upper portion of the front view image that corresponds to the stop line.

5. The system according to claim 1 wherein the controller is further programmed to detect an extracted peak from the extracted upper portion of the images using a moving average filter.

6. A system on a vehicle that provides extended detection range of a stop line on a roadway, said system comprising:
a front view camera on the vehicle, said front view camera being capable of providing a front view image of the roadway in front of the vehicle; and
a controller that is programmed to:
receive the front view image from the front view camera;
map a region of the front view image into an original bird's eye view;
detect lane markers in the original bird's eye view;
calculate a pixel intensity reference value from the detected lane markers;
extract an upper region of the front view image;
extract white line pixels from the upper region using the pixel intensity reference value;
remap the white line pixels onto an extended bird's eye view according to a camera calibration look up table;
determine a position of a stop line candidate using the white line pixels via a binarization method; and
track the position of the stop line candidate in the extended bird's eye view in subsequent extracted images.

7. The system according to claim 6 wherein a predetermined safe value is used as the reference value if lane markers are not detected in the images from the front view camera.

8. The system according to claim 6 wherein a position of the stop line is predicted using the stop line candidate position that is tracked in the following extracted images.

9. The system according to claim 6 wherein the controller is further programmed to detect an extracted peak from the extracted upper portion of the images using a moving average filter.

10. A method for providing extended detection range on a vehicle for a stop line on a roadway, said method comprising:
providing a front view camera on the vehicle that provides a front view image of the roadway in front of the vehicle; and
using a controller that is programmed to:
receive the front view image from the front view camera;
map a region of the front view image into an original bird's eye view;
detect lane markers in the original bird's eye view;
calculate a pixel intensity reference value from the detected lane markers;
extract an upper region of the front view image;
extract white line pixels from the upper region using the pixel intensity reference value;
remap the white line pixels onto an extended bird's eye view according to a camera calibration look up table;
determine a position of a stop line candidate using the white line pixels via a binarization method; and
track the position of the stop line candidate in the extended bird's eye view in subsequent extracted images.

11. The method according to claim 10 further comprising using a predetermined safe value is used as the reference value if the lane markers are not detected in the images from the front view camera.

12. The method according to claim 10 wherein the controller is further programmed to detect an extracted peak from the extracted upper portion of the front view image that corresponds to the stop line.

13. The method according to claim 10 wherein the controller is further programmed to detect an extracted peak from the extracted upper portion of the images using a moving average filter.

Assignees

• Gm Global Tech Operations Llc

Inventors

• Zhang Wende
• Hu Zhencheng

Classifications

• G06V10/36

  Applying a local operator, i.e. means to operate on image points situated in the vicinity of a given point; Non-linear local filtering operations, e.g. median filtering · CPC title

• G06F2218/04

  Denoising · CPC title

• G06V10/48

  by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation · CPC title

• G06V20/588 Primary

  Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road · CPC title

• H04N7/181 Primary

  for receiving images from a plurality of remote sources · CPC title