Detection of lane-splitting motorcycles

• US 10,311,314 B2
• Filed: 11/23/2016
• Issued: 06/04/2019
• Est. Priority Date: 11/23/2016
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Tokatyan, Shant, Athavale, Shounak
• Primary Examiner(s): Goradia, Shefali D
• Application Number:
  US15/360,856
• Publication Number:
  US 20180144200A1
• Time in Patent Office: 923 Days
• CPC Class Codes: B60Q 5/006 indicating risk of collision between vehicles or with pedestrians
• CPC Class Codes: B60Q 9/008 for anti-collision purposes
• CPC Class Codes: B60R 2300/30 characterised by the type of image processing
• CPC Class Codes: B60R 2300/301 combining image information with other obstacle sensor information, e.g. using RADAR/LIDAR/SONAR sensors for estimating risk of collision
• CPC Class Codes: B60R 2300/8066 for monitoring rearward traffic
• CPC Class Codes: B60R 2300/8093 for obstacle warning
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• 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: H04N 7/183 for receiving images from a single remote source

Abstract

A controller receives images from a rearward-facing camera having an inter-lane region in the field of view thereof. A region of interest of the images is identified corresponding to the inter-lane region. The region of interest is converted to a grayscale image having a drastically reduced number of intensity levels. A difference image is determined between the grayscale image for each image relative to the grayscale image of a preceding image. If the non-zero pixels in the difference image exceed a threshold and the area of non-zero pixels in the difference images for the input images are increasing with time, a lane-splitting vehicle will be determined to be present and an alert may be generated and/or autonomous lane changes may be suppressed.

Claims

1. A method comprising, by a vehicle controller:

converting a first image to a first grayscale image and a second image to a second grayscale image, the first and second grayscale images having a first number of intensity levels that is less than 10% of a second number of intensity levels of the first and second images; and

determining that a difference between the first grayscale image and the second grayscale image indicates a moving object.

2. The method of claim 1, further comprising:

receiving, by the vehicle controller, the first image and the second image from a rearwardly facing camera mounted to a vehicle and having an inter-lane region of the vehicle in a field of view of the rearwardly facing camera.

3. The method of claim 1, wherein converting the first image to the first grayscale image and converting the second image to the second grayscale image comprises processing only a region of interest within the first image and the second image that includes the inter-lane region.

4. The method of claim 1, wherein the first number of intensity levels is at least 256 and the second number of intensity levels is less than 10.

5. The method of claim 1, wherein the first number of intensity levels is at least 255 and the second number of intensity levels is three.

6. The method of claim 1, further comprising:

receiving, by the vehicle controller, the first image and the second image from a rearwardly facing camera mounted to a vehicle as part of a sequence of images over time;

wherein the first image is offset from the second image by between 0.3 and 0.35 seconds.

7. The method of claim 1, further comprising:

receiving, by the vehicle controller, the first image and the second image from a rearwardly facing camera mounted to a vehicle as a sequence of images over time;

wherein the first image is offset from the second image in the sequence by between 16 and 24 frames.

8. The method of claim 1, further comprising determining that the difference between the first grayscale image and the second grayscale image indicates the fast moving object comprises:

generating a difference image that is a difference between a region of interest of the first grayscale image and a region of interest of the second grayscale image; and

determining that a number of non-zero pixels of the difference image exceeds a threshold.

9. The method of claim 1, wherein determining that the difference between the first grayscale image and the second grayscale image indicates the fast moving object comprises:

generating a first difference image that is a difference between a region of interest of the first grayscale image and a region of interest of the second grayscale image; and

converting a third image to a third grayscale image;

after generating the first difference image, generating a second difference image that is a difference between a region of interest of the third grayscale image and at least one of the first grayscale image, the second grayscale image, and a different grayscale image;

determining that (a) a second number of non-zero pixels in the second difference image is greater than a first number of non-zero pixels in the first difference image and (b) that a number of non-zero pixels in at least one of the first difference image and the second difference image meets a size threshold.

10. The method of claim 1, further comprising:

in response to determining that the difference between the first grayscale image and the second grayscale image indicates a fast moving object performing, by the controller, at least one of;

generating a user perceptible alert; and

suppressing one or more lane changes.

11. A vehicle comprising:

a vehicle body;

one or more rearwardly facing cameras mounted to the vehicle body;

a controller mounted in the vehicle and programmed to—

receive a first image from the one or more rearwardly facing cameras;

receive a second image from the one or more rearwardly facing cameras after the first image;

convert the first image to a first grayscale image;

convert the second image to a second grayscale image, the first and second grayscale images having a first number of intensity levels that is less than 10 percent of a second number of intensity levels of the first and second images; and

determine that a difference between the first grayscale image and the second grayscale image indicates a moving object.

12. The vehicle of claim 11, wherein the one or more rearwardly facing cameras have an inter-lane region of the vehicle in a field of view of the rearwardly facing camera.

13. The vehicle of claim 11, wherein the controller is further programmed to convert the first image to the first grayscale image and convert the second image to the second grayscale image by processing only a region of interest within the first image and the second image, the region of interest including the inter-lane region.

14. The vehicle of claim 11, wherein the first number of intensity levels is at least 255 and the second number of intensity levels is less than 10.

15. The vehicle of claim 11, wherein the first number of intensity levels is at least 255 and the second number of intensity levels is three.

16. The vehicle of claim 11, wherein the controller is further programmed to:

receive the first image and the second image as part of a sequence of images over time;

wherein the first image is offset from the second image by between 0.3 and 0.35 seconds.

17. The vehicle of claim 11, wherein the controller is further programmed to:

receive the first image and the second image as part of a sequence of images over time;

wherein the first image is offset from the second image in the sequence by between 16 and 24 frames.

18. The vehicle of claim 11, wherein the controller is further programmed to:

generate a difference image that is a difference between a region of interest of the first grayscale image and a region of interest of the second grayscale image; and

if a number of non-zero pixels of the difference image exceeds a threshold, determine that the first grayscale image and second grayscale image indicate a moving object.

19. The vehicle of claim 11, wherein the controller is further programmed to, for a sequence of images including the first image and the second image:

convert each image to a current grayscale image;

generate a difference image by comparing the current grayscale image and a grayscale image for a preceding image of the sequence of images;

determine an amount of non-zero pixels in the difference image;

if the amount of non-zero pixels in the difference image is greater than a number of non-zero pixels in the difference image for a preceding image in the sequence of images, determine that the first grayscale image and the second grayscale image indicate movement.

20. The vehicle of claim 11, wherein the vehicle controller is further programmed to:

if the difference between the first grayscale image and the second grayscale image indicates a fast moving object perform at least one of;

generating a user perceptible alert; and

suppressing one or more lane changes.