Method and Device for Tracking a Movement of an Object or of a Person

• US 20080252725A1
• Filed: 09/21/2006
• Published: 10/16/2008
• Est. Priority Date: 09/26/2005
• Status: Abandoned Application

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Braspenning, Ralph, Lanfermann, Gerd, Benten, Harold Geardus Pieter Hendrikus
• Application Number:
  US12/067,943
• Publication Number:
  US 20080252725A1
• Time in Patent Office: Days
• US Class Current: 348/143
• CPC Class Codes: B60R 21/01538 for image processing, e.g. cameras or sensor arrays
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30268 Vehicle interior
• CPC Class Codes: G06T 7/223 using block-matching

Abstract

The invention relates to a method, a device and a computer program product for tracking a movement of an object or of a person. Tracking the movement of a person or an object by means of electronic video frames is conventional but fails if the person of object experience a sudden significant change in its translational velocity. The suggested method comprises a first step of grabbing a sequence of digital video frames and thereby capturing the object or person. At the same time measurement values of a parameter are obtained, said measurement values being indicative for the movement of the object or person being tracked by the digital video frames. In the next step the video frames are processed by means of processing logic whereby the processing logic uses a block matching algorithm, said block matching algorithm defining a pixel block in a frame and searching for this pixel block within a search area within a next frame and whereby the location of the search area within the next frame is dynamically adapted on the basis of the measurement values. The invention provides the advantage that an electronic processing of digital video frames by means of a block matching algorithm can be carried out even in those cases in which there are large changes in the velocity of the tracked object or person.

Claims

1. Method for tracking a movement of an object or of a person, the method comprising the following steps:

a) grabbing a sequence of digital video frames (1, 2) and thereby capturing the object or person (8, 8′

),

b) measuring values (measurement values) of a parameter while grabbing the video frames, said parameter being indicative for the movement of the object or person,

c) processing the video frames by means of a processing logic (12), whereby c1) the processing logic uses an algorithm which defines a pixel block (3) in a frame (1) and searches for this pixel block within a search area (7) within a next frame (2), and whereby c2) the location of the search area within the next frame is dynamically adapted on the basis of the measurement values.

2. Method according to claim 1, characterized in that for adapting the location of the search area the location of the pixel block (4) in the next frame is calculated or estimated on the basis of the measurement values.

3. Method according to claim 1, characterized in that the parameter is an acceleration vector or is a velocity vector.

4. Method according to claim 1, characterized in that the search area is either adapted for each frame, or is adapted when the measurement value is larger than a predefined threshold value.

5. Method according to claim 1, characterized in that the algorithm is a recursive search block matching algorithm.

6. Method according to claim 1, characterized in that the processing logic is implemented in hardware or is a computer program (13).

7. Method according to claim 1, characterized in that the movement of passengers (8, 8′

) within a vehicle (17) is tracked.

8. Method according to claim 1, characterized in using it for optimizing an airbag (18) inflation within a vehicle.

9. Computer program product, the computer program product comprising a computer readable medium, having thereon computer program code means, when said program is loaded, to make the computer executable for executing the following steps:

a) receiving a sequence of digital video frames (1, 2), the video frames capturing an object or a person (8, 8′

),

b) receiving values of a parameter while receiving the video frames, said parameter being indicative for the movement of the object or person,

c) processing the video frames, said processing including the sub-steps of

c1) using an algorithm which defines a pixel block (3) in a frame (1) and which searches for this pixel block within a search area (7) of a next frame (2), and whereby

c2) the location of the search area within the next frame is dynamically adapted on the basis of the measurement values.

10. Computer program product according to claim 9, characterized in that for adapting the location of the search area the location of the pixel block in the next frame is estimated on the basis of the measurement values.

11. Computer program product according to claim 9, characterized in that the search area is either adapted for each frame, or is adapted when the measurement value is larger than a predefined threshold value.

12. Device for tracking the movement of an object or of a person from a sequence of video frames, comprising:

a) a digital video camera (10) for grabbing a sequence of video frames (1, 2),

b) an input port (11, 16) for receiving values of a parameter while, said parameter being indicative for the movement of a object or a person (8, 8′

) being captured by the video frames,

c) a processing logic (12) for processing the video frames provided by the video camera, said processing logic being adapted to c1) define a pixel block (3) in a frame (1) and to search for this pixel block within a search area (7) of a next frame (2), and c2) to dynamically adapt the location of the search area within the next frame on the basis of the measurement values.

13. Device according to claim 12, characterized in that the device further includes a sensor (14) for providing the measurement values.

14. Device according to claim 13, characterized in that the sensor is an acceleration sensor.