CLASSIFICATION OF RANGE PROFILES

• US 20130041640A1
• Filed: 04/18/2011
• Published: 02/14/2013
• Est. Priority Date: 04/21/2010
• Status: Active Grant

• Current Assignee: BAE Systems Plc
• Original Assignee: BAE Systems Plc
• Inventors: Miller, Robert James
• Granted Patent: US 9,514,361 B2
• Time in Patent Office: Days
• US Class Current: 703/2
• CPC Class Codes: G01S 7/41 using analysis of echo signal for target characterisation; Target signature; Target cross-section
• CPC Class Codes: G06F 18/2415 based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
• CPC Class Codes: G06F 18/295 Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
• CPC Class Codes: G06F 2218/14 by matching peak patterns
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes

Abstract

A method and apparatus are provided for classifying range profiles, generated for example by a radar, lidar or sonar. In the method, each in a set of objects of interest is modelled with a probabilistic model. The probabilistic model represents the probabilities of occurrence of different possible sequences of distances between selected features of the object, in different orientations, that are likely to result in peaks of backscatter in a range profile of the object. The probabilistic model is derived from a first probabilistic representation of each selected feature, generated to represent the uncertainty in locating the feature and the uncertainty in observing the feature in a range profile. Classification is achieved by calculating, for each probabilistic model, the probability that the model would generate a given sequence of distances between observed backscatter events in a given range profile. The model generating the given sequence with the greatest probability identifies the object likely to have produced the given range profile. Preferably, the probabilistic models comprise Hidden Markov Models (HMMs).

Claims

1. A method for classifying range profiles, comprising:

(i) generating, for each in a set of objects of interest, a probabilistic model representing, for one or more different orientations of the object, possible sequences of distances between features of the object selected as being likely to result in distinct peaks in range data for the object, wherein the possible sequences of distances are derived from a first probabilistic representation of each said selected feature; and

(ii) classifying a given range profile by deriving an observed sequence of distances from the spacing of distinct peaks in the given range profile and by calculating, for each of one or more probabilistic models generated at step (i), the probability that the model generates the observed sequence of distances, the object whose model generates the observed sequence with the greatest probability being associated with the given range profile.

2. The method of claim 1 wherein, at step (i), generating the probabilistic model comprises the steps of:

(a) generating a first probabilistic representation defining the uncertainty in locating each of said selected features of the object and the uncertainty in whether or not each said feature is observed;

(b) deriving, for one or more orientations of the object, inferred sequences of said features which may be observable as distinct peaks in range data for the object, and the possible sequences of distances between said features in each inferred sequence; and

(c) generating, from the first probabilistic representation and the possible sequences of distances, a probabilistic model for the object from which the probability may be calculated that an observed sequence of distances corresponds to a possible sequence derived from the first probabilistic representation substrates edge abutted by edge abutting said buffers adjacent said second edges.

3. The method according to claim 1, wherein, at step (i), the probabilistic model for the object comprises a set of one or more Hidden Markov Models (HMM), each HMM defining, for a different orientation of the object, probabilities for the possible sequences of distances between said selected features of the object.

4. The method according to claim 3, wherein step (ii) further comprises estimating the orientation of an object represented in the given range profile and wherein said one or more probabilistic models comprise HMMs generated for objects having substantially said estimated orientation.

5. The method according to claim 3, further comprising the step of:

(iii) generating a plurality of examples of a range profile for one or more of said objects of interest from their respective HMMs and using a simulation technique to generate classification results for a particular set of HMMs so as to predict the potential performance of a classifier.

6. The method according to claim 1, wherein said range data and the given range profile relate to and are generated by a high range resolution radar, and wherein said distinct peaks correspond to peaks in backscattered radiation from the object.

7. The method according to claim 1, wherein said range data and the given range profile relate to and are generated by a lidar.

8. The method according claim 1, wherein said range data and the given range profile relate to and are generated by a sonar.

14. A computer program, which when loaded onto a general purpose computer and executed, implements the method according to claim 1.

15. A computer program product comprising a data carrier having stored thereon software code means which, when loaded into a general purpose computer and executed, implement the method according to claim 1.

9. An apparatus for classifying range profiles, comprising:

an input for receiving a range profile to be classified;

a store for storing, for each of one or more objects of interest, a probabilistic model derived from a first probabilistic representation of features of the object selected as being likely to result in distinct peaks in range data for the object; and

classifying means for deriving a sequence of distances from the spacing of distinct peaks in a received range profile, for calculating, for the received range profile and for each of one or more probabilistic models stored in the store, the probability that the stored probabilistic model generates the derived sequence of distances, and for associating the received range profile with an object from said one or more objects of interest whose probabilistic model generates the derived sequence with the highest probability.

10. The apparatus according to claim 9, wherein the probabilistic model comprises a set of one or more HMMs, each defining, for a different orientation of the object, probabilities for the possible sequences of distances between said selected features of the object.

11. The apparatus according to claim 9, wherein said range data and the given range profile related to and are generated by a high range-resolution radar.

12. The apparatus according to claim 9, wherein said range data and the given range profile related to and are generated by a lidar.

13. The apparatus according to claim 9, wherein said range data and the given range profile related to and are generated by a sonar.