Method and device for stabilizing images supplied by a video camera

• US 7,656,424 B2
• Filed: 08/11/2005
• Issued: 02/02/2010
• Est. Priority Date: 09/08/2004
• Status: Active Grant

• Current Assignee: Citilog Co.
• Original Assignee: Citilog Co.
• Inventors: Bouzar, Salah
• Primary Examiner(s): Tran; Sinh
• Assistant Examiner(s): Negron; Wanda M
• Application Number:
  US11/661,982
• Publication Number:
  US 20070263096A1
• Time in Patent Office: 1,636 Days
• Field of Search: None
• US Class Current: 348/149
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors
• CPC Class Codes: H04N 23/68 for stable pick-up of the scene, e.g. compensating for camera body vibrations
• CPC Class Codes: H04N 23/6811 based on the image signal
• CPC Class Codes: H04N 23/6812 based on additional sensors, e.g. acceleration sensors
• CPC Class Codes: H04N 23/682 Vibration or motion blur correction

Abstract

Method and device for stabilizing images obtained by a video camera of an environment with objects moving along lanes. The method a first stage of determining in first images obtained by the camera, portions corresponding to the movement lanes, determining the remaining second portions complementary to the first portions, determining, in the second portions, the reference position of the image point corresponding to a first stationary object point, and a second stage of determining in at least one second image taken after the first images, the vector that corresponds to the movement of the image point relative to its reference position determined by the first images, and processing the second image as a function of the modulus and direction of the vector such that, relative to the three-dimensional frame of reference the image point returns to its reference position.

Claims

1. A method of stabilizing images obtained by a controllable video camera (1) of an environment that has a given three-dimensional frame of reference associated therewith and in which objects (4) can move on preferred lanes (5), the method comprising:

a first stage;

determining via a computer processor, in a stable first images (20) obtained by the controllable camera, first portions (21) that correspond to the preferred movement lanes (5) for said objects (4);

then

determining in said first images, by a differential process, remaining second portions (22) that are complementary to the first portions; and

then

determining, in said remaining second portions (22), the reference position of the image point (P_i) corresponding to a first stationary object point (P_o) belonging to said environment (3), said first stationary object point having brightness different from the brightness of the zone of the environment that surrounds it; and

a second stage following the first;

determining in at least one second image (30) taken by the controllable camera (1) after said first images (20), the vector (V_d) corresponding to the movement of said image point relative to its reference position determined with said first images; and

in processing the second image (30) output by the controllable camera as a function of the modulus and the direction of said vector (V_d) in such a manner that relative to said three-dimensional frame of reference associated with the environment, said image point (P_i) returns to its reference position.

2. The method according to claim 1, further comprising:

in the first stage;

determining, in the remaining second portions (22), the reference position of a second image point corresponding to a two second stationary object point belonging to the environment, the two stationary object points having brightness different from that of the zone of the environment that surrounds them; and

in the second stage following the first;

determining in the second image (30) taken by the controllable camera after the first images, firstly the vector corresponding to the movement of at least one of the two image points, and secondly first and second parameters representing respectively the variation in the distance between these two images points and the value of the angle between the two straight lines passing through the two image points respectively in the first images and in the second image; and

processing the second image output by the controllable camera as a function of the modulus and the direction of the vector and as a function of the first and second parameters so that relative to the three-dimensional frame of reference associated with the environment, both image points return to their reference positions.

3. The method according to claim 1, further comprising:

selecting at least one of the first stationary object point and a second stationary object point to be situated on the horizon line of said environment.

4. The method according to claim 2, further comprising selecting at least one of the two stationary object points to be situated on the horizon line of said environment.

5. A device enabling stabilizing images obtained by a controllable video camera (1) of an environment that has a given three-dimensional frame of reference associated therewith and in which objects (4) can move on preferred lanes (5), the device comprising:

a computer processor programmed to provide;

means for determining, in stable first images (20) obtained by the controllable camera (1), first portions (21) corresponding to the preferred travel lanes (5) of the objects (4);

means for determining in these first images (20), by a differential process, remaining second portions (22) that are complementary to the first portions;

means for determining, in said remaining second portions (22), the reference position of an image point corresponding to a first stationary object point belonging to the environment, this first stationary object point having brightness different from that of the zone of the environment that surrounds it;

means for determining in at least one second image (30) taken by the controllable camera (1) after the first images, the vector (V_d) that corresponds to the movement of the image point relative to its reference position as determined with the first images; and

means for processing the second image (30) output by the controllable camera as a function of the modulus and the direction of said vector so that, relative to the three-dimensional frame of reference associated with the environment, the image point returns to its reference position so that the second image remains stationary.