System and method for autonomous joint detection-classification and tracking of acoustic signals of interest

1. A method for autonomous joint detection-classification and tracking of targets of interest, the method comprising:

receiving a plurality of acoustic signals from a plurality of acoustic sensors, each of the respective acoustic signals characterized by time-series data;

detecting a target of interest from the received acoustic signals by:

(i) transforming the received acoustic signals from the time domain to the frequency domain;

(ii) generating a relative-bearing beam response for each of the transformed signals in one or more beam steering directions;

(iii) estimating the median background noise level of the relative-bearing beam response in each of the one or more beam steering directions and normalizing the spectral response of the relative-bearing beam response by the estimated background noise level, wherein a normalized spectral response is produced that is associated with each relative-bearing beam response;

(iv) performing a joint detection-classification operation, wherein the joint detection-classification operation comprises a selective frequency integration of the normalized spectral response associated with each relative-bearing beam response, wherein the frequency integration is informed by the detailed physics of the underlying classifier for the target of interest to satisfy a spatial and spectral target hypothesis of the classifier;

(v) computing a detection surface in bearing and time based on the frequency integration of the joint detection-classification operation;

(vi) determining a decision surface in bearing and time by calculating a constant-false-alarm-rate (CFAR) detection threshold from the estimated noise background level and applying the constant-false-alarm-rate detection threshold to the detection surface; and

(vii) associating decision surface threshold exceedances with the target, and thereby detecting the target.

2. The method of claim 1 , wherein the plurality of acoustic sensors includes a microphone.

3. The method of claim 1 , further comprising generating a target rack corresponding to the decision surface by:

(i) associating decision surface threshold exceedances to produce a relative-bearing track as a function of bearing and time;

(ii) calculating a true bearing track corresponding to each of the relative-bearing tracks by reconciling the relative-bearing tracks with an estimate of hydrophone sensor array orientation; and

(iii) transforming the acoustic signals from the frequency domain to the time domain using the relative-bearing track to generate the target track.

4. The method of claim 3 , further comprising:

generating a summary report of spectral data associated with each target track; and

outputting a compressed data report identifying the characteristics of the generated target track included in the generated summary report.

5. The method of claim 3 , wherein prior to transforming the received acoustic signals from the time domain to the frequency domain, the acoustic signals are conditioned for bias detection and removal, inoperative channel shading, transient suppression, sidelobe suppression, and/or sub-aperture phase alignment.

6. The method of claim 1 , wherein generating a relative-bearing beam response for each of the transformed acoustic signals includes using linear or data adaptive methods to compute the spatial filter weighting coefficients of the beamformer required to generate each relative-bearing beam response.

7. The method of claim 1 , wherein generating a relative-bearing beam response for each of the transformed signals in one or more beam steering directions includes generating a relative bearing beam response in one or more beam steering directions spanning the azimuthal beamspace from forward endfire to aft endfire.

8. The method of claim 1 , wherein the received acoustic signals are transformed from the frequency domain to the time domain using an inverse Fast Fourier Transform algorithm.

9. The method of claim 1 , wherein generating a target track further includes generating a target track and scissorgram for further classification.

10. A system for autonomous joint detection-classification, and tracking of targets of interest, the system comprising:

(A) a microphone sensor array configured to receive and transmit a plurality of acoustic signals;

(B) a host platform including a memory module, a communications module, a global positioning system receiver and one or more embedded processors, the one or more embedded processors configured to autonomously:

(1) receive acoustic signals from a plurality of microphone sensors, each of the respective acoustic signals characterized by time-series data;

(2) detect a target of interest corresponding to each of the respective received acoustic signals by,

(a) transforming the received acoustic signals from the time domain to the frequency domain;

(b) generating a relative-bearing beam response for each of the transformed signals in one or more beam steering directions;

(c) estimating the median background noise level of the relative-bearing beam response in each of the one or more beam steering directions and normalizing the spectral response of the relative-bearing beam response by the estimated background noise level, wherein a normalized spectral response is produced that is associated with each relative-bearing beam response;

(d) performing a joint detection-classification operation, wherein the joint detection-classification operation comprises a selective frequency integration of the normalized spectral response associated with each relative-bearing beam response, wherein the frequency integration is constrained by the detailed physics of the underlying classifier for the target of interest to satisfy a spatial and spectral target hypothesis of the classifier;

(e) computing a detection surface in bearing and time based on the frequency integration of the joint detection-classification operation;

(f) determining a decision surface in bearing and time by calculating a constant-falsealarm-rate (CFAR) detection threshold from the estimated background noise level and applying the constant-false-alarm-rate detection threshold to the detection surface; and

(e) generating a target track corresponding to the decision surface by,

(i) associating decision surface threshold exceedances to produce a relative-bearing track as a function of bearing and time;

(ii) calculating a true bearing track corresponding to each of the relative-bearing tracks by reconciling the relative bearing tracks with an estimate of microphone sensor array orientation; and

(iii) transforming the received acoustic signals from the frequency domain to the time domain using the relative-bearing track; generating a summary report of spectral data associated with each target track; and

(f) producing as an output a compressed data report identifying the characteristics of the generated target track included in the generated summary report.

11. The system of claim 10 , wherein the microphone sensor array is external to the host platform.

12. The system of claim 10 , wherein the microphone sensor array is configured to be towed by the host platform.

13. The system of claim 10 , wherein the microphone sensor array is mounted on the host platform.

14. The system of claim 10 , wherein the host platform comprises a marine vehicle platform that is propelled using an electric-motor driven propeller, a buoyancy-based propulsion system, or a propulsion system powered by wave energy.

15. The system of claim 14 , wherein a separate surrogate marine vehicle platform is further configured to transmit target of interest-like signals from known locations allowing the quantification of parameters associated with each generated target track including one or more of detection probability, detection false alarm probability, classification probability, classification false alarm probability, system processing gain and bearing errors.

16. The system of claim 10 , wherein the microphone sensor array includes one of a multichannel hydrophone sensor, a linear hydrophone sensor, a planar hydrophone sensor, a mobile hydrophone sensor, a fixed hydrophone sensor, or a passive hydrophone sensor.

17. The system of claim 10 , wherein prior to transforming the received acoustic signals from the time domain to the frequency domain, the acoustic signals are conditioned for bias detection and removal, inoperative channel shading, transient suppression, sidelobe suppression, and/or sub-aperture phase alignment.

18. The system of claim 10 , wherein generating a relative-bearing beam response for each of the transformed acoustic signals includes using linear or data-adaptive methods to compute the spatial filter weighting coefficients of the beamformer required to generate each relative-bearing beam response.

19. The system of claim 10 , wherein generating a relative-bearing beam response for each of the transformed signals in one or more beam steering directions includes generating a relative bearing beam response in one or more beam steering directions spanning the azimuthal beamspace from forward endfire to aft endfire.

20. The system of claim 10 , wherein a time-synchronized acoustic signal is transmitted from a separate vehicle platform and used to calibrate the one or more embedded processors to achieve increased joint detection-classification performance and decreased detection false alarm rates.