Estimating objects proper motion using optical flow, kinematics and depth information

• US 8,422,741 B2
• Filed: 08/21/2008
• Issued: 04/16/2013
• Est. Priority Date: 08/22/2007
• Status: Expired due to Fees

• Current Assignee: Honda Research Institute Europe GmbH (Honda Motor Company)
• Original Assignee: Honda Research Institute Europe GmbH (Honda Motor Company)
• Inventors: Eggert, Julian, Rebhan, Sven, Schmudderich, Jens, Willert, Volker
• Primary Examiner(s): Wang, Claire X
• Assistant Examiner(s): JAMES, THOMAS AIDEN
• Application Number:
  US12/599,201
• Publication Number:
  US 20110243390A1
• Time in Patent Office: 1,699 Days
• Field of Search: None
• US Class Current: 382/107
• CPC Class Codes: G06T 7/269 using gradient-based methods

Abstract

The invention relates to a method for detecting the proper motion of an real-world object, comprising the steps of acquiring, by an image capturing device (ICD), a first image (I₁) of the object at a first point in time (t₁) and a second image (I₂) at a second point in time (t₂); obtaining a third (hypothetical) image (I₃), based on an estimated effect of the motion of the image capturing device (ICD) itself (EMF) between the first and the second point in time (t₁, t₂), wherein the effect of the motion of the image capturing device (ICD) itself is estimated based on the forward kinematics of the image capturing device; determining an optical flow (OF) between the second image (I₂) and the third image (I₃); and evaluating the optical flow (OF) by incorporating uncertainties of the optical flow (OF) and the ego-motion-flow (EMF) in order to determine the proper motion of the object.

Claims

1. A method for detecting proper motion of real-world objects in an image from an image capturing device, the method comprising the steps of:

acquiring, by an image capturing device, a first image of an object at a first point in time and a second image at a second point in time;

acquiring depth information for each pixel of the first image and the second image,

computing a third image, based on the first image or the second image as well as estimated ego-motion of the image capturing device itself between the first point and the second point in time, wherein the ego-motion is estimated based on forward kinematics of the image capturing device and depth information for each pixel of the first image;

computing an ego motion-compensated optical flow by comparing the second image and the third image; and

determining proper motion of the object by evaluating the optical flow based on a likelihood that the optical flow and the estimated ego-motion are consistent with the same physical velocity.

2. The method according to claim 1, wherein the depth information for the first image is estimated based on binocular disparity.

3. The method according to claim 2, wherein an invalid estimated depth is replaced by a depth model gained from valid estimated depths.

4. The method according to claim 1, wherein the step of computing the third image comprises warping the first image.

5. The method according to claim 1, wherein the step of computing the third image comprises warping the second image.

6. A mobile autonomous vehicle controlled by the method according to claim 1.

7. The mobile autonomous vehicle according to claim 6, wherein the mobile autonomous vehicle is an autonomous robot.

8. A system for detecting proper motion of real-world objects in an image from an image capturing device, the system comprising:

means for acquiring, by an image capturing device, a first image of an object at a first point in time and a second image at a second point in time;

means for acquiring depth information for each pixel of the first image and the second image,

means for computing a third image, based on an estimated effect of motion of the image capturing device itself between the first point and the second point in time, wherein the effect of the motion of the image capturing device itself is estimated based on forward kinematics of the image capturing device and depth information for each pixel of the first image;

means for determining an ego motion-compensated optical flow by comparing the second image and the third image; and

means for determining proper motion of the object by evaluating the optical flow based on a likelihood that the optical flow and the estimated ego-motion are consistent with the same physical velocity by incorporating uncertainties of the optical flow and ego-motion-flow in order to determine the proper motion of the object.