Method and apparatus for ground detection and removal in vision systems

• US 7,068,815 B2
• Filed: 03/31/2004
• Issued: 06/27/2006
• Est. Priority Date: 06/13/2003
• Status: Active Grant

• Current Assignee: Ford Motor Company, SRI International, Inc.
• Original Assignee: Sarnoff Corporation (SRI International, Inc.)
• Inventors: Chang, Peng, Hirvonen, David, Camus, Theodore Armand
• Primary Examiner(s): Johns, Andrew W.
• Assistant Examiner(s): EDWARDS, PATRICK L
• Application Number:
  US10/813,768
• Publication Number:
  US 20040252864A1
• Time in Patent Office: 818 Days
• Field of Search: 382/103, 382/104, 382/106, 382/154, 382/285, 382/291, 382/107, 356/3, 356/3.02, 356/3.08, 356/3.11, 356/3.13, 356/3.14, 356/3.16, 356/4.01, 356/4.06, 356/12, 356/611, 702/166, 702/5, 702/16, 340/854.1, 340/435, 340/686.6, 340/937, 701/208, 348/140, 359/458, 359/462, 359/470, 342/180, 33/204, 409/115
• US Class Current: 382/106
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 20/00 Scenes; Scene-specific elements control of digital cameras H04N23/60
• 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

Abstract

A vision system that forms a map of a scene proximate a platform, e.g., a vehicle, that determines the actual ground plane form the map, and that corrects the map for differences between the actual ground plane and an assumed ground plane. The vision system may remove the actual ground plane from the map to prevent false positives. The vision system can further identify and classify objects and, if appropriate, take evasive action.

Claims

1. A method of performing vision processing comprising:

stereo imaging a scene about a platform to produce stereo image data;

producing a map of data from the stereo image data, wherein the map is based on an assumed ground plane;

identifying an actual ground plane using the map;

compensating the map for differences between the actual ground plane and the assumed ground plane; and

removing the actual ground plane from the map.

2. The method of claim 1 further including the step of comparing a plurality of templates to the map to identifying a match between the map and at least one template.

3. The method of claim 2 further including the step of adjusting a parameter of the platform in response to a match.

4. The method of claim 3 wherein the parameter of a vehicle comprises at least one parameter selected from the group of:

an air bag deployment parameter, a seatbelt parameter, a vehicle height parameter, and a vehicle velocity and/or acceleration control parameter.

5. The method of claim 3 further including accessing at least one template from a database comprising a plurality of templates.

6. The method of claim 2 wherein the comparing step includes determining a difference between each pixel in the map and each similarly positioned pixel in a template, and determining that a pixel is a match if the difference at each pixel is less than a predefined amount.

7. A computer readable medium storing a vision system program that controls a computer to:

produce a depth map from input imagery;

determine an actual ground plane from said depth map;

correct the depth map based on the actual ground plane;

detect a potential threat in said corrected depth map;

estimate a size of said detected potential threat;

estimate a position of said detected potential threat;

estimate a velocity of said detected potential threat;

perform a trajectory analysis of said detected potential threat using said estimated position and said estimated velocity;

perform a collision prediction based on said trajectory analysis; and

determine if a collision is imminent based on said collision prediction and on said estimated size of said potential threat.

8. The computer readable medium of claim 7 that further controls a computer to remove the actual ground from the corrected depth map.

9. A collision avoidance system comprising:

a collision detection system comprising;

a stereo camera pair for producing imagery of a scene;

a stereo image preprocessor for preprocessing said imagery;

a map generator for producing from said preprocessed imagery a map referenced to an assumed ground plane; and

a target processor for determining the actual ground plane from said map and for removing that ground plane from said map.

10. A computer readable medium storing a vision system program that controls a computer to:

produce a depth map from input imagery;

determine an actual ground plane from said depth map; and

removing the actual ground from the depth map.