Enhanced adaptive statistical filter providing improved performance for target motion analysis noise discrimination

• US 5,511,042 A
• Filed: 05/25/1995
• Issued: 04/23/1996
• Est. Priority Date: 05/25/1995
• Status: Expired due to Fees

• Current Assignee: the united states of america as represented by the secretary of the navy
• Original Assignee: the united states of america as represented by the secretary of the navy
• Inventors: O'Brien, Francis J. Jr.
• Primary Examiner(s): Pihulic, Daniel T.
• Application Number:
  US08/449,475
• Time in Patent Office: 334 Days
• Field of Search: 367/135, 367/901, 367/118, 364/517, 364/574, 364/724.19
• US Class Current: 367/135
• CPC Class Codes: G01S 13/723 by using numerical data
• CPC Class Codes: H03H 21/0029 based on statistics
• CPC Class Codes: H03H 21/003 KALMAN filters

Abstract

An adaptive statistical filter system for receiving a data stream compris a series of data values from a sensor associated with successive points in time. Each data value includes a data component representative of the motion of a target and a noise component, with the noise components of data values associated with proximate points in time being correlated. The adaptive statistical filter system includes a prewhitener, a plurality of statistical filters of different orders, correlation mensuration and decorrelator module and a selector. The prewhitener generates a corrected data stream comprising corrected data values, each including a data component and a time-correlated noise component. The plural statistical filters receive the corrected data stream and generate coefficient values to fit the corrected data stream to a polynomial of corresponding order and fit values representative of the degree of fit of corrected data stream to the polynomial. The correlation mensuration and decorrelation module performs a hypothesis test to determine whether the degree of correlation is statistically significant, and, if it is, generates decorrelated fit values using an autoregressive moving average methodology which assesses the noise components of the statistical filter. The selector receives the decorrelated fit values and coefficient values from the plural statistical filters and selects coefficient values from one of the filters in response to the decorrelated fit values. The coefficient values are coupled to a target motion analysis module which determines position and velocity of a target.

Claims

1. An adaptive statistical filter system for receiving data streams comprising a series of data values from a sensor associated with successive points in time, each said data value including a data component representative of the kinematics of the relative positions of an object and the sensor and a noise component, with the noise components of data values associated with proximate points in time being correlated, the system including:

a prewhitener for receiving the data stream from the sensor and generating a corrected data stream, the corrected data stream comprising a series of corrected data values each associated with a data value of the data stream, each including a data component and a noise component with the noise components of data values associated with proximate points in time being decorrelated;

plural statistical filters of different orders coupled to receive said corrected data stream in parallel from said prewhitener, each statistical filter generating coefficient values to fit the corrected data stream to a polynomial of corresponding order and fit values representative of the degree of fit of the corrected data stream to the polynomial;

correlation mensuration and decorrelation means for receiving the fit values and generating a respective decorrelated fit value therefrom for each order filter in accordance with an autoregressive moving average methodology;

selection means for receiving the decorrelated fit values and coefficient values from the stochastic decorrelation means and selecting one of said filters in response to the decorrelated fit values; and

the coefficient values of the selected filter being used by a object motion analysis module to determine the position and velocity of the object.

2. An adaptive statistical filter system as defined in claim 1 in which each said adaptive statistical filter comprises a Kalman filter.

3. An adaptive statistical filter system as defined in claim 1 in which said selection means performs a pair-wise F-test operation in connection with said fit values provided by said statistical filters of adjacent order, and selects one of said filters in response to the F-test operation.

4. An adaptive statistical filter system as defined in claim 3 in which said selection means selects the highest-ordered one of said statistical filters for which the pair-wise F-test operation provides an F-statistic above a predetermined threshold value.

5. An adaptive statistical filter system as defined in claim 1 in which said sensor generates each data value over a selected time window, with time windows for proximate data values overlapping, in which case the noise components of the proximate data values will be correlated, the prewhitener generating a correction factor that reflects the degree of correlation of the noise component and using the correction factor to generate the corrected data values for the corrected data stream.

6. An adaptive statistical filter system as defined in claim 5 in which the prewhitener generates the correction factor for each data value using the correction factor for the previous data value.

7. An adaptive statistical filter system as defined in claim 6 in which the prewhitener generates the correction factor as a first-order autoregression arrangement in which the correlation between noise components of a data value and a prior data value is

8. An adaptive statistical filter system as defined in claim 7 in which the sensor generates each data value using a selected integration arrangement for integrating values of signals received over said time window, and the factor "p" is selected in response to the selected integration arrangement.

9. An adaptive statistical filter system as defined in claim 8 in which the selected integration arrangement is an exponential arrangement, in which each data value generated by the sensor associated with a selected time is generated in response to values of signals received over the time window prior to the selected time, with the contribution of signal values to the data value diminishing in a selected exponential relationship to the time interval from the selected time, the prewhitener using as factor "p" a value corresponding to p=e(^-T/s), where "s" is the period of the time window, "T" is the time period between the end of successive time windows and "e" is the mathematical constant (approximately 2.71828).

10. An adaptive statistical filter system as defined in claim 1 in which said correlation mensuration and decorrelation means comprises:

inter-residual correlation value generating means for generating, for a series of fit values for each order filter, an inter-residual correlation value reflecting a correlation among said fit values, and for determining whether the inter-residual correlation value is statistically significant;

orthogonal error structure value generating means for generating, for each fit value, for each order filter, an orthogonal error structure value in response to the inter-residual correlation value generated by the inter-residual correlation value generating means; and

iteration control means for controlling the inter-residual correlation value generating means and the orthogonal error structure value generating means through a series of iterations, the iteration control means enabling (i) the inter-residual correlation value generating means to use the fit values from the filters in generating the respective inter-residual correlation values in the first iteration, and to use the orthogonal error structure values in generating the respective inter-residual correlation values in subsequent iterations, and (ii) the orthogonal error structure value generating means to generate an orthogonal error structure value if the inter-residual correlation value generating means determines that the inter-residual correlation value is statistically significant, and to provide the orthogonal error value to the selection means as the decorrelated fit value if the inter-residual correlation value generating means determines that the inter-residual correlation value is not statistically significant.

11. An adaptive statistical filter system as defined in claim 10 in which said inter-residual correlation value generating means generates each inter-residual correlation value κ

as ##EQU3## where E_i (t_T) corresponds to the fit value provided by the filter of order "i" at time t_T.

12. An adaptive statistical filter system as defined in claim 10 in which said orthogonal error structure value generating means generates said orthogonal error structure value E_i *(t_T) for each filter of order "i" at each time t_T as