HAZARD DETECTION FROM A CAMERA IN A SCENE WITH MOVING SHADOWS

• US 20150371096A1
• Filed: 06/12/2015
• Published: 12/24/2015
• Est. Priority Date: 06/18/2014
• Status: Active Grant

• Current Assignee: MobilEye Vision Technologies Ltd. (Intel Corporation)
• Original Assignee: MobilEye Vision Technologies Ltd. (Intel Corporation)
• Inventors: Stein, Gideon, Dagan, Erez
• Granted Patent: US 9,892,328 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 7/248 involving reference images or patches
• CPC Class Codes: G06T 7/40 Analysis of texture depth or shape recovery from texture G06T7/529
• 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: H04N 7/183 for receiving images from a single remote source

Abstract

Computerized methods are performable by a driver assistance system while the host vehicle is moving. The driver assistance system includes a camera connectible to a processor. First and second image frames are captured from the field of view of the camera. Corresponding image points of the road are tracked from the first image frame to the second image frame. Image motion between the corresponding image points of the road is processed to detect a hazard in the road. The corresponding image points are determined to be of a moving shadow cast on the road to avoid a false positive detection of a hazard in the road or the corresponding image points are determined not to be of a moving shadow cast on the road to verify detection of a hazard in the road.

Claims

1. A computerized method for detection of a hazard in a road, the method performable by a driver assistance system mountable in a host vehicle while the host vehicle is moving, wherein the driver assistance system includes a camera operatively connectible to a processor, the method comprising:

capturing a first image frame and a second image frame from the field of view of the camera;

tracking corresponding image points of the road from said first image frame to said second image frame

processing image motion between the corresponding image points of the road, wherein said processing of image motion is used to detect a hazard in the road;

determining that the corresponding image points are of a moving shadow cast on the road, thereby avoiding a false positive detection of a hazard in the road or determining that the corresponding image points are not of a moving shadow cast on the road, thereby verifying detection of a hazard in the road.

2. The method of claim 1, further comprising:

hypothesizing that the image motion is consistent with a hypothetical static object in the road;

projecting a bottom edge on the road plane of the hypothesized static object onto the image frames;

rejecting the hypothesis that the image motion is caused by a static object in the road if there is no strong horizontal texture at the hypothesized projected bottom edge of the static object or if the texture of hypothesized bottom edge of the static object is changing over the image frames, and confirming thereby that the image motion is caused by the moving shadow, or confirming the hypothesis that the image motion is caused by a static object in the road if there is a strong horizontal texture at the hypothesized projected bottom edge of the static object and if the texture of hypothesized bottom edge of the static object is fixed over the image frames.

3. The method of claim 1, further comprising:

recognizing in the image frames, images of a moving vehicle;

associating the image motion between the corresponding image points of the road with the images of a moving vehicle, thereby determining the image motion between the corresponding image points of the road is due to a moving shadow cast from the moving vehicle.

4. The method of claim 3, further comprising:

hypothesizing that the image motion is due to a hypothetical moving shadow cast from the moving vehicle;

computing respective distances to the hypothetical moving shadow and

matching the distances to the hypothetical moving shadow with distances to the moving vehicle, thereby confirming the hypothesis that the image motion is due to the moving shadow cast from the moving vehicle.

5. The method of claim 3, further comprising:

hypothesizing that the image motion is due to a hypothetical moving shadow cast from the moving vehicle;

determining relative speed between the host vehicle to the moving vehicle;

calculating image motion of points on the road for the relative speed between the host vehicle and the moving vehicle;

measuring image motion of the hypothetical moving shadow;

comparing the measured image motion of the hypothetical moving shadow to the calculated image motion for the relative speed between the host vehicle and the moving vehicle; and

confirming the hypothesis that the moving image points are of a moving shadow cast from the moving vehicle if the measured image motion matches the calculated image motion.

6. The method of claim 1, further comprising:

associating image motion with a moving shadow when consistent with a static hazard in the road of height greater than a threshold height.

7. The method of claim 1, further comprising:

recognizing images of a lane mark in the road;

associating image motion with a moving shadow by detecting the image motion superimposed over the images of the lane mark.

8. The method of claim 7, further comprising:

associating image motion with a moving shadow when the image motion is similar on both sides of the images of the lane mark.

9. The method of claim 1, further comprising:

providing location information of an object suspected to cast a moving shadow;

finding a plurality of lines in the image frames between the shadow and the image of the object; and

searching along the lines to correlate the image motion of the object suspected to cast a moving shadow and the motion of the shadow.

10. The method of claim 1, further comprising:

verifying that the image motion is due to a moving shadow when the image motion is not aligned with the focus of expansion or when direction of the image motion changes sign.

11. The method of claim 1, further comprising:

performing texture analysis on an image of an object suspected to cast a moving shadow to determine if the image of the object has at least one texture selected from the group consisting of ;

branch texture and leaf texture.

12. The method of claim 1, further comprising:

recognizing an image of a street lamp;

verifying that the image motion is due to a moving shadow from the light of the street lamp by constructing lines between the image of the street lamp, the image of the tree casting the moving shadow and the moving shadow.

13. A driver assistance system mountable in a host vehicle, the driver assistance system including a camera operatively connectible to a processor, the system configured, while the host vehicle is moving, to:

capture a first image frame and a second image frame from the field of view of the camera;

track corresponding image points of the road from said first image frame to said second image frame

process image motion between the corresponding image points of the road to detect a hazard in the road;

determine that the corresponding image points are of a moving shadow cast on the road to avoid a false positive detection of a hazard in the road or determine that the corresponding image points are not of a moving shadow cast on the road to verify detection of a hazard in the road.

14. The driver assistance system of claim 13, further configured to:

hypothesize that the image motion is consistent with a hypothetical static object in the road;

project a bottom edge on the road plane of the hypothesized static object onto the image frames;

reject the hypothesis that the image motion is caused by a static object in the road if there is no strong horizontal texture at the hypothesized projected bottom edge of the static object or if the texture of hypothesized bottom edge of the static object changes over the image frames to confirm that the image motion is caused by the moving shadow.

15. The driver assistance system of claim 13, further configured to:

recognize in the image frames, images of a moving vehicle;

associate the image motion between the corresponding image points of the road with the images of a moving vehicle to determine that the image motion between the corresponding image points of the road is due to a moving shadow cast from the moving vehicle.

16. The driver assistance system of claim 13, further configured to:

recognize image of a lane mark in the road;

associate image motion with a moving shadow by detecting the image motion superimposed over the images of the lane mark.

17. The driver assistance system of claim 13, further configured to:

provide location information of an object suspected to cast a moving shadow;

find a plurality of lines in the image frames between the shadow and the image of the object; and

search along the lines to correlate the image motion of the object suspected to cast a moving shadow and the motion of the shadow.

18. The driver assistance system of claim 13, further configured to:

verify that the image motion is due to a moving shadow when the image motion is not aligned with the focus of expansion or when direction of the image motion changes sign.

19. The driver assistance system of claim 13, further configured to:

perform texture analysis on an image of an object suspected to cast a moving shadow to determine if the image of the object has at least one texture selected from the group consisting of ;

branch texture and leaf texture.

20. The driver assistance system of claim 13, further configured to:

recognize an image of a street lamp;

verify that the image motion is due to a moving shadow from the light of the street lamp by constructing lines between the image of the street lamp, the image of the tree casting the moving shadow and the moving shadow.