Virtual observer

• US 9,420,234 B2
• Filed: 04/13/2007
• Issued: 08/16/2016
• Est. Priority Date: 04/13/2006
• Status: Expired due to Fees

• Current Assignee: Virtual Observer Pty., Ltd. (DTI Group Limited)
• Original Assignee: Virtual Observer Pty., Ltd. (DTI Group Limited)
• Inventors: Greenhill, Stewart Ellis Smith, Venkatesh, Svetha
• Primary Examiner(s): Fan, Hua
• Application Number:
  US12/297,118
• Publication Number:
  US 20090073265A1
• Time in Patent Office: 3,413 Days
• Field of Search: 348/148, 348/143, 348/153, 348/159, 348/161, 348/129
• US Class Current: 1/1
• CPC Class Codes: G08B 13/19647 Systems specially adapted for intrusion detection in or around a vehicle
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

This invention concerns wide-area video surveillance systems. In a first aspect the invention is a surveillance network, in another aspect the invention is a virtual observer, and in a further aspect the invention is a method for operating a virtual observer. Each segments or frame of video, from each camera of the network is associated with the following trajectory parameters; a time and a spatial position, and possibly a radius, orientation, resolution and field of view, and stored for later recall.

Claims

1. A system for reconstructing a scene observed by a virtual observer in a wide area video surveillance network comprising:

(a) plural mobile video cameras mounted on different vehicles that move in the wide area video surveillance network, the plural mobile video cameras having an external view, and wherein each segment or frame of video recorded by the plural mobile video cameras is stored together with corresponding trajectory parameters including a time of the segment or frame of video, a spatial position of a first camera of the plural mobile video cameras, orientation of the first camera, resolution of the first camera and field of view of the first camera;

(b) a computer to recall segments or frames of the stored video in response to receiving one or more queries that include observation parameters, so as to enable a view from the virtual observer representing an imaginary camera located at a point in the wide area video surveillance network, the view being defined by the observation parameters and the observation parameters including a source position of the imaginary camera, orientation of the imaginary camera, resolution of the imaginary camera, field of view of the imaginary camera, and visibility radius of the field of view of the imaginary camera by synthesizing together recalled segments or frames that;

(i) were recorded at different times by the plural mobile video cameras mounted on the different vehicles, when the different vehicles pass through the virtual observer, and

(ii) have trajectory parameters that match the observation parameters,

wherein the synthesizing together the recalled segments or frames includes an operation to merge the recalled segments or frames; and

(c) a monitor to display the view from the virtual observer.

2. The system according to claim 1, wherein the view:

from a panoramic view where the desired field of view is wider than the camera view, comprising multiple images taken at different times combined to give a wide-angle perspective view.

3. The system according to claim 2, wherein the view is a view from a “

time-lapse”

view showing how a view of a place changes over time.

4. The system according to claim 2, wherein the view is a view from a view of a particular object or landmark.

5. The system according to claim 2, wherein the view is selected on the basis of multiple spatial, temporal and geometric constraints.

6. The system according to claim 1, wherein there are also static cameras in the wide area video surveillance network.

7. A method of reconstructing a scene observed by a

virtual observer in a wide area video surveillance network, comprising the following steps:

receiving one or more queries including observation parameters;

recalling stored segments or frames of video based on the one or more queries, wherein the stored segments or frames of video are recorded by a plurality of mobile video cameras having an external view and mounted on different vehicles that move in the wide area video surveillance network, and wherein each segment or frame of video recorded by the plurality of mobile video cameras is stored together with corresponding trajectory parameters including a time of the segment or frame of video, a spatial position of a first camera of the plurality of mobile video cameras, orientation of the first camera, resolution of the first camera and field of view of the first camera; and

constructing a view to be displayed from a virtual observer representing an imaginary camera located at a point in the wide area video surveillance network given queried observation parameters including a source position of the imaginary camera, orientation of the imaginary camera, resolution of the imaginary camera, field of view of the imaginary camera, and visibility radius of the field of view of the imaginary camera, wherein the view is constructed by synthesizing together recalled video segments or frames that;

(i) were recorded at different times by the plurality of mobile video cameras mounted on the different vehicles, when the different vehicles pass through the virtual observer, and

(ii) have trajectory parameters that match the observation parameters and

wherein the synthesizing together the recalled segments or frames includes an operation to merge the recalled segments or frames.

8. A method according to claim 7, wherein at least one query defines a closest observation query that returns a segments or frame taken from the closest point to a defined location.

9. A method according to claim 7, wherein the view displayed is updated from time to time.

10. The method according to claim 7, wherein at least one query defines a view towards a place that returns segments or frames that view a defined location.

11. The method according to claim 7, wherein at least one query defines a view from a place that returns segments or frames looking outward from a defined location.

12. The method according to claim 7, wherein at least one query defines a view of a large spatial region that returns segments or frames captured in the region.