Object identification via data fusion

• US 8,260,052 B1
• Filed: 11/30/2010
• Issued: 09/04/2012
• Est. Priority Date: 11/30/2010
• Status: Active Grant

• Current Assignee: Raytheon Company (Rtx Corporation)
• Original Assignee: Raytheon Company (Rtx Corporation)
• Inventors: Tgavalekos, Nora T., Scannell, Brian J., Nelson, Kenric P., Phelps, Ethan
• Primary Examiner(s): Brainard, Timothy A
• Application Number:
  US12/956,637
• Time in Patent Office: 644 Days
• Field of Search: 382/181, 342/90
• US Class Current: 382/181
• CPC Class Codes: G01S 13/723 by using numerical data
• CPC Class Codes: G01S 13/86 Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
• CPC Class Codes: G01S 7/41 using analysis of echo signal for target characterisation; Target signature; Target cross-section
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition

Abstract

The technology described herein includes a system and/or a method for identifying an object. The technology includes determining an alpha parameter that is associated with a fusion function. The technology includes determining a beta parameter that is associated with a degree of expected independence of a received set of data and the received set of data including information associated with a classification of the object. The technology includes fusing the received set of data based on the alpha parameter and the beta parameter. The technology includes generating a probability of identification of the classification of the object based on the fused data.

Claims

1. A system for identifying an object, the system comprising:

an alpha parameter module configured to determine an alpha parameter, the alpha parameter associated with a fusion function;

a beta parameter module configured to determine a beta parameter, the beta parameter associated with a degree of expected independence of a received set of data and the received set of data comprising information associated with a classification of the object;

a data fusion module configured to fuse the received set of data based on the alpha parameter and the beta parameter; and

a probability of identification module configured to generate a probability of identification of the classification of the object based on the fused data.

2. The system of claim 1, further comprising a communication module configured to receive the set of data at a plurality of times, the plurality of times being near a time.

3. The system of claim 2, further comprising:

the communication module further configured to receive a set of second data at a second plurality of times, the second plurality of times being near a second time, and the time being different from the second time;

the data fusion module further configured to fuse the received set of second data based on the alpha parameter and the beta parameter; and

the probability of identification module further configured to generate a second probability of identification based on the fused data and the second fused data.

4. The system of claim 3, further comprising a multi-look data module configured to request the received set of second data based on the probability of identification.

5. The system of claim 3, further comprising a multi-look data module configured to prioritize a request for the received set of second data based on one or more resource parameters associated with the system.

6. The system of claim 1, wherein the probability of identification is indicative of the identified object being a target object.

7. The system of claim 1, wherein the received set of data comprising radar signal data.

8. The system of claim 1, further comprising a communication module configured to receive the set of data from a plurality of data sources.

9. The system of claim 1, wherein the fused data is calculated in accordance with equation:

If any |α

_i|<

TOL

$\mathrm{If}<br><br><br><br>\underset{j=1}{\overset{N}{\sum <br><br>}}<br><br>w_j<<br><br>1$$W_i=1$
else

$W_i={\left[\underset{j=1}{\overset{N}{\sum <br><br>}}<br><br>w_j\right]}^{{\mathrm{\beta <br><br>}}_i-1}$$P<br><br>\left({\mathrm{\omega <br><br>}}_i|x_1,x_2,\mathrm{\dots <br><br>}<br><br>,x_N\right)=\frac{P<br><br>\left({\mathrm{\omega <br><br>}}_i\right)<br><br>{\left(\underset{j=1}{\overset{N}{\prod <br><br>}}<br><br><br><br>{P<br><br>\left({\mathrm{\omega <br><br>}}_i|x_j\right)}^{w_j}\right)}^{W_i}}{\underset{k=1}{\overset{C}{\sum <br><br>}}<br><br>\left[P<br><br>\left({\mathrm{\omega <br><br>}}_k\right)<br><br>{\left(\underset{j=1}{\overset{N}{\prod <br><br>}}<br><br><br><br>{P<br><br>\left({\mathrm{\omega <br><br>}}_i|x_j\right)}^{w_j}\right)}^{W_k}\right]}$
else

$V=\underset{j=1}{\overset{N}{\sum <br><br>}}<br><br>w_j$$\mathrm{If}<br><br><br><br>\underset{j=1}{\overset{N}{\sum <br><br>}}<br><br>w_j<<br><br>1$$W_i=V$
else

10. A method, implemented on a processor, for identifying an object, the method comprising:

determining an alpha parameter, the alpha parameter associated with a fusion function;

determining a beta parameter, the beta parameter associated with a degree of expected independence of a received set of data and the received set of data comprising information associated with a classification of the object;

fusing the received set of data based on the alpha parameter and the beta parameter; and

generating a probability of identification of the classification of the object based on the fused data.

11. The method of claim 10, further comprising selecting the fusion function based on the alpha parameter and the beta parameter.

12. The method of claim 11, wherein the fusion function is a quadratic mean function, an average function, a log-average function, a harmonic mean function, or an independent product rule function.

13. The method of claim 11, the method further comprising extrapolating the fusion function based on the alpha parameter and the beta parameter.

14. The method of claim 11, the method further comprising interpolating the fusion function based on the alpha parameter and the beta parameter.

15. The method of claim 10, wherein the received set of data comprising a plurality of object classification probabilities, the plurality of object classification probabilities comprising information associated with the object at a plurality of sequential times, and

the fusing the received set of data based on the alpha parameter and the beta parameter further comprising fusing the plurality of object classification probabilities based on the alpha parameter and the beta parameter.

16. The method of claim 10, wherein the fused data is calculated in accordance with equation:

If any |α

_i|<

TOL

$\mathrm{If}<br><br><br><br>\underset{j=1}{\overset{N}{\sum <br><br>}}<br><br>w_j<<br><br>1$$W_i=1$
else

$W_i={\left[\underset{j=1}{\overset{N}{\sum <br><br>}}<br><br>w_j\right]}^{{\mathrm{\beta <br><br>}}_i-1}$$P<br><br>\left({\mathrm{\omega <br><br>}}_i|x_1,x_2,\mathrm{\dots <br><br>}<br><br>,x_N\right)=\frac{P<br><br>\left({\mathrm{\omega <br><br>}}_i\right)<br><br>{\left(\underset{j=1}{\overset{N}{\prod <br><br>}}<br><br><br><br>{P<br><br>\left({\mathrm{\omega <br><br>}}_i|x_j\right)}^{w_j}\right)}^{W_i}}{\underset{k=1}{\overset{C}{\sum <br><br>}}<br><br>\left[P<br><br>\left({\mathrm{\omega <br><br>}}_k\right)<br><br>{\left(\underset{j=1}{\overset{N}{\prod <br><br>}}<br><br><br><br>{P<br><br>\left({\mathrm{\omega <br><br>}}_i|x_j\right)}^{w_j}\right)}^{W_k}\right]}$
else

$V=\underset{j=1}{\overset{N}{\sum <br><br>}}<br><br>w_j$$\mathrm{If}<br><br><br><br>\underset{j=1}{\overset{N}{\sum <br><br>}}<br><br>w_j<<br><br>1$$W_i=V$
else

17. A computer program product, tangibly embodied in an information carrier, the computer program product including instructions being operable to cause a data processing apparatus to:

determine an alpha parameter, the alpha parameter associated with a fusion function;

determine a beta parameter, the beta parameter associated with a degree of expected independence of a received set of data and the received set of data comprising information associated with a classification of the object;

fuse the received set of data based on the alpha parameter and the beta parameter; and

generate a probability of identification of the classification of the object based on the fused data.