System and method for tracking moving objects

• US 8,792,680 B2
• Filed: 12/19/2012
• Issued: 07/29/2014
• Est. Priority Date: 06/23/2005
• Status: Active Grant

• Current Assignee: Israel Aerospace Industries Limited (Government of Israel)
• Original Assignee: Israel Aerospace Industries Limited (Government of Israel)
• Inventors: Karazi, Uri
• Primary Examiner(s): Abdi, Amara
• Application Number:
  US13/720,844
• Publication Number:
  US 20130108111A1
• Time in Patent Office: 587 Days
• Field of Search: 382/103, 348/148, 348/169, 706/905
• US Class Current: 382/103
• CPC Class Codes: G01S 5/16 using electromagnetic waves other than radio waves
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10032 Satellite or aerial image; Remote sensing
• CPC Class Codes: G06T 2207/20104 Interactive definition of region of interest [ROI]
• CPC Class Codes: G06T 2207/30212 Military
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

A method for tracking an object that is embedded within images of a scene, including: in a sensor unit, generating, storing and transmitting over a communication link a succession of images of a scene. In a remote control unit, receiving the images, receiving a command for selecting an object of interest in a given image and determining object data associated with the object and transmitting the object data to the sensor unit. In the sensor unit, identifying the given image and the object of interest using the object data, and tracking the object in other images. If the object cannot be located in the latest image of the stored succession of images, using information of images in which the object was located to predict estimated real-time location thereof and generating direction commands to the movable sensor for generating realtime images of the scene and locking on the object.

Claims

1. A method for selecting a moving object of interest in a succession of images of a scene, the succession of images being generated by a remote sensor unit communicating with a control unit through a communication link, the method comprising:

in the remote sensor unit;

receiving from the control unit data indicative of estimated future coarse location of a selected moving object in the succession of images of the scene, wherein the moving object is selected in the control unit while a time delay exists resulting from a timing difference between a first timing that the image including the moving object is generated in the remote sensor and a second timing in which the moving object is located in a real-time image at the control unit, and a third timing when the data from the control unit is received by the sensor unit;

generating a further succession of images of an area in the scene, the area including the estimated future coarse location of the selected moving object,

comparing between at least two images of said further succession of images, and in the case of a difference in at least a respective portion of the area that includes the coarse location of the selected moving object in the at least two images meets a given threshold, the difference, in a later image, is identified as a candidate of the selected moving object; and

executing, in the remote sensor, substantially real-time location of a selected moving object notwithstanding the time delay.

2. The method according to claim 1, wherein said threshold being one member of a group that includes:

(i) changing of values of at least n pixels in the image, (ii) changing of values of at least n pixels in the image by at least m value delta.

3. The method according to claim 1, wherein said threshold being cluster of pixels whose gray level values were changed.

4. The method according to claim 1, further comprising generating at least one additional image and locating the candidate object in said at last one additional image.

5. The method according to claim 1, further comprising identifying said candidate object as sought object according to at least one of the following criterion:

location of the candidate object, speed of the candidate object, acceleration of the candidate object, size of the candidate object, shape of the candidate object, color of the candidate object being a cluster of pixels whose gray level value was changed.

6. The method according to claim 1, wherein said coarse location being estimated coordinates of future location of the object of interest.

7. The method according to claim 1, wherein said comparison includes subtraction of images.

8. The method according to claim 1, wherein said comparison includes correlation of images.

9. The method according to claim 1, further comprising applying stabilization techniques to selected images.

10. The method according to claim 1, further comprising, using real-time location data for controlling payload means.

11. The method according to claim 10, wherein said payload means including a designator for illuminating said object of interest.

12. The method according to claim 10, wherein said payload means including kill mechanism for killing the object.

13. The method according to claim 10, wherein said payload means including data collection device for collecting data in respect of the object.

14. The method according to claim 13, wherein said data is collected for intelligence applications.

15. The method according to claim 1 wherein said generating comprising:

opening a tracking window, said tracking window accommodating the estimated future coarse location of said object; and

acquiring a succession of images of an area selected in said tracking window.

18. The method according to claim 1 further comprising selecting the moving object in the control unit;

the selection is performed by an operator of the control unit.

16. A system comprising:

a sensor unit that includes movable sensor, the sensor unit is configured to generate a succession of images of a scene, a remote control unit configured to communicate with the sensor unit through a communication link and receive through the link at least said succession of images, and transmit through said link object data that pertain to an object that is embedded in images of the scene, in response to selection, at the control unit, of the object in an image;

the system is configured to accomplish substantially real-time location of the object notwithstanding a time delay constituted by a timing difference between a first timing that an image including the object is generated in said sensor and a second timing in which said object is located in real-time image at the control unit, and a third timing when data from the control unit are received by the sensor unit;

wherein the sensor unit is configured to

receive, from the control unit, data indicative of estimated future coarse location of a selected moving object in the succession of images of the scene;

generate a further succession of images of an area in the scene, the area including the estimated future coarse location of the selected moving object;

compare between the area in at least two images of said succession; and

in case a difference in at least a respective portion of the area that includes the coarse location of the selected moving object in the at least two images meets a given threshold, identify the difference, in a later image, as a candidate of the selected moving object.

17. The system according to claim 16 wherein said generation of a succession of images comprises:

opening a tracking window, said tracking window accommodating the estimated future coarse location of said object; and

acquiring a succession of images of an area selected in said tracking window.

19. A computer-readable non-transitory storage medium containing instructions that causes a computer to perform a process for selecting a moving object of interest in a succession of images of a scene, the succession of images being generated by a remote sensor unit communicating with a control unit through a communication link, the process comprising:

in the remote sensor unit;

receiving from the control unit data indicative of estimated future coarse location of a selected moving object in the succession of images of the scene, wherein the moving object is selected in the control unit while a time delay exists resulting from a timing difference between a first timing that the image including the moving object is generated in the remote sensor and a second timing in which the moving object is located in real-time image at the control unit, and a third timing when the data from the control unit is received by the sensor unit;

generating a further succession of images of an area in the scene, the area including the estimated future coarse location of the selected moving object,

comparing between at least two images of said further succession of images, and in the case of a difference in at least a respective portion of the area that includes the coarse location of the selected moving object in the at least two images meets a given threshold, the difference, in a later image, is identified as a candidate of the selected moving object; and

executing, in the remote sensor, substantially real-time location of a selected moving object notwithstanding the time delay.