Method and device for determining the position of an object within a given area

• US 6,834,116 B2
• Filed: 10/23/2001
• Issued: 12/21/2004
• Est. Priority Date: 04/23/1999
• Status: Expired due to Fees

• Current Assignee: Continental Automotive GmbH (Continental AG)
• Original Assignee: Siemens AG
• Inventors: Zittlau, Dirk, Ertl, Ludwig, Köhler, Thorsten
• Primary Examiner(s): CHANG, JON CARLTON
• Application Number:
  US10/014,419
• Publication Number:
  US 20020085739A1
• Time in Patent Office: 1,155 Days
• Field of Search: 382/103, 382/104, 382/107, 382/199, 382/236, 382/291, 382/216, 382/209, 382/217, 382/218, 382/220, 348/143, 348/148, 280/735, 701/45
• US Class Current: 382/103
• CPC Class Codes: B60R 21/01538 for image processing, e.g. cameras or sensor arrays
• CPC Class Codes: B60R 21/01552 detecting position of specific human body parts, e.g. face, eyes or hands
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G06T 7/74 involving reference images or patches

Abstract

Within a given area, the position of the head of the front seat passenger in a vehicle is determined by producing a differential image, in which only the contour of the moving object appears, from two frames that are recorded one after the other by a video camera. The contours of the differential images are used to calculate the position.

Claims

1. A method for determining the position of a moveable object within a given area, which comprises:

taking a sequence of frames of a given area with a video camera and calculating a current position of an object in the given area by electronically evaluating the frames of the sequence;

comparing a currently taken one of the frames with a previously stored one of the frames to produce a differential image in which a contour of the object appears only when the object moves; and

calculating the position of the object based on the differential image; and

when the object is located within a predetermined region;

a1) calculating a current differential image;

b1) extracting a current contour of the object form the current differential image;

c1) after initiation, defining a first contour and using the first contour as a template, and for all further contours, incorporating the current contour into the template in a weighted manner; and

d1) repetitively performing steps a1 through c1 in order.

2. The method according to claim 1, wherein the object is a head of a front seat passenger in a vehicle.

3. The method according to claim 1, which comprises, if the object moves out of the predetermined region:

a2) calculating a current differential image;

b2) extracting a current contour from the current differential image;

c2) calculating the position of the object using a cross-correlation of the current contour with the template;

d2) if a magnitude of the correlation exceeds a predefined amount, centering a measuring window on the current contour, replacing the template with the current contour, and going to step e2);

in an absence of a differential image, jumping to step a2);

otherwise jumping to step a1);

e2) if the contour is again within the predetermined region;

jumping to step a1);

f2) if the contour moves in a predetermined warning region, issuing an alarm signal; and

h2) jumping to step a2).

4. A device for determined the position of a moveable object within a given area, comprising:

a video camera with a defined frame sequence time;

a control unit with a computer unit;

a frame storage device; and

evaluation software configured to perform the method according to claim 1.

5. The device according to claim 4, wherein said frame storage device has a capacity for storing at least five frames.

6. The device according to claim 4, wherein said video camera is a camera selected from the group consisting of a CCD camera and a CMOS camera.

7. The device for determining the position of a moveable object according to claim 4, wherein:

the object is a head of a passenger in a front seat of a vehicle having a dashboard;

said video camera has an optical axis and is configured such that the optical axis is aligned approximately perpendicularly with respect to a plane in which movements of the passenger normally take place between the front seat and the dashboard; and

said camera captures images a region between the passenger and the dashboard.

8. The device according to claim 7, comprising:

an airbag control device activated dependent on a prediction of when the head of the passenger will penetrate into a hazard range;

said prediction based on a trajectory of the head and a speed of the head.

9. The device according to claim 4, comprising an infrared light source, said video camera provided with a filter that cuts out wavelengths below a near infrared spectrum range.

10. The device according to claim 4, wherein said control device receives an emergency braking signal when an emergency braking occurs.