4D GIS based virtual reality for moving target prediction

• US 8,229,163 B2
• Filed: 08/22/2008
• Issued: 07/24/2012
• Est. Priority Date: 08/22/2007
• Status: Active Grant

• Current Assignee: American GNC Corporation
• Original Assignee: American GNC Corporation
• Inventors: Coleman, Norman P., Lin, Ching-Fang
• Primary Examiner(s): Repko, Jason M
• Assistant Examiner(s): Nakhjavan, Shervin
• Application Number:
  US12/229,450
• Publication Number:
  US 20090087029A1
• Time in Patent Office: 1,432 Days
• Field of Search: 382/103, 382/106, 382/165, 382/181, 348/169, 342/76, 342/95
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30212 Military
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 20/13 Satellite images
• CPC Class Codes: G06V 20/647 by matching two-dimensional images to three-dimensional objects

Abstract

The technology of the 4D-GIS system deploys a GIS-based algorithm used to determine the location of a moving target through registering the terrain image obtained from a Moving Target Indication (MTI) sensor or small Unmanned Aerial Vehicle (UAV) camera with the digital map from GIS. For motion prediction the target state is estimated using an Extended Kalman Filter (EKF). In order to enhance the prediction of the moving target'"'"'s trajectory a fuzzy logic reasoning algorithm is used to estimate the destination of a moving target through synthesizing data from GIS, target statistics, tactics and other past experience derived information, such as, likely moving direction of targets in correlation with the nature of the terrain and surmised mission.

Claims

1. A method of 4D GIS based virtual reality for moving target prediction, comprising the steps of:

(a) recognizing a predetermined terrain and a plurality of predetermined targets;

(b) positioning and tracking said targets;

(c) estimating and reasoning a predetermined destination; and

(d) predicting movement route and traiectory of said moving target,

wherein said step (a) further comprises steps of;

(a1) obtaining terrain and moving target image from a Moving Target Indication (MTI) sensor or an Unmanned Aerial Vehicle (UAV) camera;

(a2) extracting moving targets by subtraction from a sequence of measurements from said MTI sensor or said Unmanned Aerial Vehicle (UAV) camera;

(a3) recognizing said moving target using pattern recognition;

(a4) classifying terrain background through a statistical model based image classifier; and

(a5) registering said classified terrain with a digital map from GIS through matching recognized culture (man-made) objects and natural objects.

2. The method as recited in claim 1, wherein in step (b) further comprises steps of:

(b1) determining a position of said moving target after said terrain image registration;

(b2) retrieving geographical information where said moving target is located from said GIS; and

(b3) obtaining status variables of said moving target by tracking said target movements on said digital map.

3. The method as recited in claim 2, in step (c) wherein a fuzzy logic reasoning algorithm is used to synthesize multi-modalities from GIS, target statistics, tactics and other military information to estimate the destination of said moving targets.

4. The method as recited in claim 3, in step (d) wherein two algorithms are used to estimate the trajectory for road-dependent targets and road-independent targets respectively, wherein for road-dependent targets, a road network is used as constraint for motion prediction and tracking;

and for road-independent targets, a time-varying adaptive algorithm is used for motion prediction based on said moving target mobility and terrain environment.

5. The method, as recited in claim 4, wherein said terrain and moving target image is obtained by an imaging sensor, wherein said imaging sensor provides measurements of target range, position, and attitude, which are fused with other object detection sensors for obstacle tracking.

6. The method, as recited in claim 5, wherein an Adaptive Multimode Tracking (AMT) System is employed to compensate for the limitations of said individual object detecting sensor, and to improve the overall object detection and tracking performance.

7. The method, as recited in claim 6, wherein said terrain and moving target image is obtained by an imaging sensor, wherein said imaging sensor provides measurements of target range, position, and attitude, which are fused with other object detection sensors for obstacle tracking.

8. The method, as recited in claim 7, in step (d) wherein a real-time 4D GIS-based virtual reality for simulating said moving target and possible aimpoint within a Common Operating Picture (COP) is produced.

9. The method, as recited in claim 8, wherein said step (d) further comprises steps of:

(d1) retrieving geographic data of said area wherein said moving target may be located according to said position prediction;

(d2) generating a virtual 3D terrain basing on regular Digital Elevation Model (DEM), or Triangulated Irregular Network (TIN);

(d3) generating a virtual vehicle according to a 3D Vehicle Model Library; and

(d4) producing a virtual reality of said predicted moving target movements by combining said virtual terrain, said virtual targets, and said predicted trajectory.

10. The method, as recited in claim 9, wherein said virtual reality is interacted by users through a Graphic User Interface (GUI) to control the display.

11. The method, as recited in claim 9, further comprising the steps of:

(e) receiving platform rotation commands of a device using a desired pointing direction of said device and a current attitude measurement of said device, wherein said rotation commands are computed according to the predicted movement route and trajectory of said moving target;

(f) combining said computed platform rotation commands with feedback signals;

(g) computing an automatic stabilization and positioning control signal by a servo controller;

(h) amplifying servo controller signals;

(i) sending said amplified servo controller signals to an actuator;

(j) converting electric signals to torques and said torque exerted on a platform body to eliminate interference to said platform body; and

(k) sensing a motion of said platform body and feedback a sensor signal to said servo controller.

12. The method as recited in claim 1, in step (d) wherein two algorithms are used to estimate the trajectory for road-dependent targets and road-independent targets respectively, wherein for road-dependent targets, a road network is used as constraint for motion prediction and tracking;

and for road-independent targets, a time-varying adaptive algorithm is used for motion prediction based on said moving target mobility and terrain environment.

13. The method, as recited in claim 1, further comprising the steps of:

(e) receiving platform rotation commands of a device using a desired pointing direction of said device and a current attitude measurement of said device, wherein said rotation commands are computed according to the predicted movement route and trajectory of said moving target;

(f) combining said computed platform rotation commands with feedback signals;

(g) computing an automatic stabilization and positioning control signal by a servo controller;

(h) amplifying servo controller signals;

(i) sending said amplified servo controller signals to an actuator;

(j) converting electric signals to torques and said torque exerted on a platform body to eliminate interference to said platform body; and

(k) sensing a motion of said platform body and feedback a sensor signal to said servo controller.