DENSE STRUCTURE FROM MOTION

• US 20140161323A1
• Filed: 02/18/2014
• Published: 06/12/2014
• Est. Priority Date: 09/21/2010
• Status: Active Grant

• Current Assignee: Mobileye Technologies Limited (Intel Corporation)
• Original Assignee: Mobileye Technologies Limited (Intel Corporation)
• Inventors: Livyatan, Harel, Berberian, Oded, Stein, Gideon, Cohen, Barak
• Granted Patent: US 9,959,595 B2
• Time in Patent Office: Days
• US Class Current: 382/107
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 3/18 Image warping, e.g. rearranging pixels individually
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/579 from motion
• 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

Abstract

Determining three-dimensional structure in a road environment using a system mountable in a host vehicle including a camera connectible to a processor. Multiple image frames are captured in the field of view of the camera. In the image frames, a line is selected below which the road is imaged. The line separates between upper images essentially excluding images of the road and lower images essentially including images of the road. One or more of the lower images is warped, according to a road homography to produce at least one warped lower image. The three-dimensional structure may be provided from motion of a matching feature within the upper images or from motion of a matching feature within at least one of the lower images and at least one warped lower image.

Claims

1. A method for determining three-dimensional structure in a road environment, the method performed by a system mountable in a host vehicle, wherein the system includes a camera operatively connectible to a processor, the method comprising:

capturing a plurality of image frames in the field of view of the camera;

in the image frames selecting a line below which the road is imaged, wherein the line separates between upper images essentially excluding images of the road and lower images essentially including images of the road; and

warping at least one of the lower images according to a road homography to produce at least one warped lower image.

2. The method of claim 1, further comprising:

warping at least one of the image frames according to ego-motion of the host vehicle.

3. The method of claim 1, further comprising.

providing the three-dimensional structure from motion of a matching feature within the upper images.

4. The method of claim 1, further comprising:

providing the three-dimensional structure from motion of a matching feature within at least one of the lower images and said at least one warped lower image.

5. The method of claim 1, further comprising:

first matching a feature between said lower images which are unwarped to produce a first matching result;

second matching said feature between at least one of said unwarped lower images and said at least one warped lower image to produce a second matching result; and

selecting an image disparity for said feature, corresponding to a matching result selected from the group consisting of said first matching result and said second matching result.

6. The method of claim 1, further comprising:

from a disparity map of said at least one warped lower image, determining which image points are of the road;

selecting an image disparity for said image points of the road from matching features of said at least one warped lower image.

7. The method of claim 1, further comprising:

pre-warping an image portion in the image frames corresponding to a vertical plane perpendicular to the direction of travel at a distance Z from the vehicle, wherein the distance Z is selectably either a fixed value or dependent on vehicle motion.

8. The method of claim 1, further comprising:

pre-warping an image portion in the image frames corresponding to two vertical planes parallel to the direction of travel at a fixed distance to the left and right of the camera.

9. The method of claim 1, further comprising:

said capturing at least three image frames in the field of view of the camera of the road environment, a first image frame at time A, a second image frame at time B and a third image frame at time C, wherein the time interval (C-A) is significantly greater than the time interval (B-A), wherein an epipole is a stationary point on image transformation between the at least three image frames;

for an image feature near the epipole, computing image motion between the third image frame captured at time C and the first image frame captured at time A;

for an image feature far from the epipole, computing image motion from the second image frame captured at time B and the first image frame captured.

10. The method of claim 1, further comprising:

reducing image resolution of the image frames by performing a local histogram equalization around a matching feature within the image frames ;

providing the three-dimensional structure from motion of said matching feature within the image frames of reduced resolution.

11. The method of claim 1, further comprising:

performing a rank transform on the image frames prior to computing motion disparity between the image frames, wherein the rank transform replaces a gray-scale of a picture element with a count of pixels in a local neighborhood of the picture element which have a lower gray-scale value than the picture element.

12. A system for determining three-dimensional structure in a road environment, the system mountable in a host vehicle, including a camera operatively connectible to a processor, the system operable to:

capture a plurality of image frames in the field of view of the camera;

in the image frames, select a line below which the road is imaged, wherein the line separates between upper images essentially excluding images of the road and lower images essentially including images of the road; and

warp at least one of the lower images according to a road homography to produce at least one warped lower image.

13. The system of claim 12, further operable to:

warp at least one of the image frames according to ego-motion of the host vehicle.

14. The system of claim 12, further operable to:

provide the three-dimensional structure from motion of a matching feature within the upper images.

15. The system of claim 12, further operable to:

provide the three-dimensional structure from motion of a matching feature within at least one of the lower images and said at least one warped lower image.