Sequential Adaptive Multi-Modality Target Detec-tion and Classification using Physics-Based Models

1
Sequential Adaptive Multi-Modality Target
Detec-tion and Classification using Physics-Based
Models

• Professor Andrew E. Yagle (PI) (EECS)
• Signal and image processing, inverse
  scattering
• Professor Alfred O. Hero III (EECS)
• Statistics, signal and image processing
• Professor Kamal Sarabandi (Director, Rad Lab)
• Scattering, inverse scattering, remote
  sensing
• Assistant Professor Marcin Bownik (Mathematics)
• Wavelets, functional analysis and
  approximation

2
Sequential Adaptive Multi-Modality Target
Detec-tion and Classification using Physics-Based
Models

• PROJECT SUPERVISION
• Dr. Douglas Cochran (DARPA)
• Dr. Russell Harmon (ARO)
• INDUSTRY COLLABORATION
• Veridian (formerly ERIM) of Ann Arbor

3
Research Project Objectives

• Develop overall algorithm for sequential
  detection, sensor management selection
• Develop physics-based models
• Simplify physics-based models using
  functional-analysis-based approximation
• Evaluate the resulting procedure on realistic
  models (statistical simulations) and real data

4
Issues Overall Algorithm

• How to select sensing modalities?
• What is value-added for combining other
  modalities? Is it worth additional cost?
• How do we implement data-adaptive
  configu-rations, e.g., selection of
  sources/receivers, based on scattering of targets
  and propagation in medium?
• What are the figures of merit?
• How to select decision thresholds?

5
Practical Applications

• Develop a set of signal processing/statistics
  al-gorithms to solve multi-modal sensing problems
  
• Examples
• Detection of tanks under trees
• vehicles under canopy of tree foliage
• Detection of buried objects (land mines)

6
Issues Physics-Based Models

• Scattering models
• Hard targets of different types (vehicle, mines,
  etc.)
• Clutter of different types (trees, rough
  surfaces, etc.)
• Propagation models, e.g., tree canopies
  (attenuation, phase deformation, dispersion,
  etc.)
• Sensor models
• Radar, SAR, IR, etc.
• Frequency, polarization, incidence angle, etc.
• Model order reduction
• Using function approximation, e.g., wavelets

7
Issues Evaluation of Results

• Behavior of algorithm on realistic models (UM
  Radiation Lab).
• Benchmarking against physics-based models.
• Figures-of-merit for evaluation of algorithm
• Behavior of algorithm on real data

8
Overall Algorithm Overview

• Sequential feedback structure Detectibility for
  given sensor waveform/source/receiver used to
  guide future sensor selection
• Possible targets organized into tree structure
  leading to sequence of binary classifications
• Inverse filter based on physics-based model used
  to improve performance of the above

9
Overall Algorithm Overview
10
Target Detector/Classifier

• Hybrid hypothesis tests (majority rules)
• Bayes optimal test Optimal, but requires
  Bayesian priors for unknown parameters
• GLRT Use maximum likelihood estimates (MLE) for
  unknown parameters
• Maximal Invariant Project data onto subspace on
  which density functions are independent of
  unknown parameters

11
Target Detector/Classifier

• EXAMPLE ATR
• 1 of 9 imagesbelow hidden in image above
  (forest-grassy plain)
• Location column 305 at the A/B boundary
• Clutter clutter-only reference chips used

A
B
12
Target Detector/Classifier

• RESULTS ATR
• Structured Kelly standard ATR GLRT
• Figure-of-merit min. detectable target amp.
• MI best with 200 chips
• GLR best with 250
• Hence need hybrid test

TEST TYPE 200 CHIPS 250 CHIPS
maxim. invar. 0.0609 0.0145
GLR 1 0.104 0.0146
Struct. Kelly 0.105 0.0141
13
Target Detector/Classifier

• SAR imaging none of these 3 better than rest
• We propose to use all 3 and let majority rule
• Apply log(P) times to distinguish P possible
  target types (different models of tanks, mines)
  organized into a tree structure (known models)
• Conditional pdf unknown parameters Orientation,
  location, reflectivity of target Propagation
  characteristics of the medium

14
Target Detector/Classifier
Vehicle type
HMMWV
Tank
T72
Orientation
15
(No Transcript)
16
Physics-Based Models

• Need models to develop conditional pdfs
• Fast include target, medium, sensor
  characteristics, with unknown parameters
• Evaluation of integrals in Bayes optimal test
  Monte Carlo marginalization too slow for us.
• Sequential Importance Sampling
  Denumerable-source blind deconvolution Digital
  multi-user communications (real-time)

17
Physics-Based Models

• Models needed for propagation and targets
• Models include unknown random parameters (e.g.,
  wavelet coefficients-see the following)
• Use Monte-Carlo-type simulations to obtain
  non-parametric estimates of pdfs for these
• Validate these with real data for targets/clutter
• Result statistical models of targets and clutter

18
Physics-Based Models
SAR image of tree stand using VV polarization
Fractal generated tree stand
19
Physics-Based Models

• Problem Both the propagation and vehicle models
  are very complicated mathematically
• Too complicated to be used as is in algorithm
• Need To simplify models so they can be used
• How Expand Greens functions in efficient basis
  functions. Wavelets have proven to be very useful
  in electromagnetic modeling

20
Physics-Based Models

• Solution Need data-adaptive basis functions
  (precludes multipole expansions)
• Adaptive anisotropic wavelet basis functions
  which are non-separable are more general and
  allow direction-dependent resolutions
• Precomputed basis functions for different
  physical situations (e.g., forest types, season)
• Try Best Basis algorithm, Basis Pursuit

21
(No Transcript)
22
Detectibility Computer

• Issue Should we use/deploy another sensor?
• Sensor Radar, acoustic, infrared and different
  frequencies polarizations of radar (Both type
  and waveform of various sources)
• Need To compute value-added for another sensor
  Improvement in Edetectibility - cost. Choose
  the sensor which maximizes this.
• Formulation Dynamic stochastic scheduling

23
Detectibility Computer

• Cost Penalty for deploying another sensor
• Dollar cost of a UAV or other sensor times
  Printerception and destruction of new sensor
• Time cost in switching antennae types
• Power cost in operating power and weight

24
Detectibility Computer

• Detectibility What does this mean?
• Optimal Use min Prdetection as criterion.
• But Too difficult to compute in real-time
  Unknown target, unknown medium, etc.
• Hence Use easier-to-compute detectibility as a
  surrogate function for Prdetection.
• Then Choose sensor that maximizes
  Edetectibility-cost based on previous data.

25
Detectibility Computer

• Detectibility What do we use for this?
• Renyi information divergence This is
• Much easier to compute (see next slide)
• Related to Prdetection by error exponent
• Equals Kullback-Liebler distance between null
  model and most-likely target model for the
  special case a 1. Choose 0 lt a lt 1.

26
Detectibility Computer

• Renyi Information Divergence RID
• Log Prerror lt (1-a)RID so figure-of-merit.
• Y past data N Nth model 0 null model.
• Conditional densities computed quickly with
  sequential importance sampling (see previous)
  Also may use particle filtering.

27
Mine Detection AcousticRadar

• One possible scenario of combining modalities
• Acoustic source vibrates buried objects
• Vibration significant at resonant frequencies
• Radar source images vibrating objects
• Doppler radar spectrum exhibits sharp peaks at
  resonant acoustic frequencies of objects
• Use to identify shape and material of objects
• Use this information in turn to detect mines

28
Mine Detection AcousticRadar
29
Mine Detection Multiple Sensors

• Problem False alarms time-consuming Must treat
  each as if it is a real mine
• Problem Failure-to-detects disastrous!
• Single-sensor technology is insufficient
• Hybrid sensor modalities seem necessary to attain
  both very low PrF and high PrD
• Multi-modal approach seems promising

30
Tanks Under Trees Radar Sensor

• Present work with ARL Tanks Under Trees
• 3-D MMW (millimeter wave) radar image
• Ka-band image of HMMWV on platform
• HMMWV parked under deciduous canopy
• (UM/ARL field experiment in July 2000)
• We are equipped for realistic work on this

31
Tanks Under Trees Radar Sensor
32
Tanks Under Trees Radar Sensor

• Problems Multiple scattering off of the ground,
  trunk, leaves, branches, vehicle
• Unknown presence and type of vehicles
• Unknown orientation, location, reflectivity of
  vehicles (unknown parameters in models)
• Unknown radar propagation characteristics through
  the atmosphere

33
Tanks Under Trees Radar Sensor
34
Tanks Under Trees Radar Sensor

• Solutions UM Radiation Lab has basic models for
  radar scattering off of vehicles
• Parametrized by a few unknown parameters
  (position, orientation, reflectivity, etc.)
• UM Radiation Lab also has good models for radar
  scattering off of tree canopies
• Parametrized by a few unknown parameters (average
  leaf area, branch and trunk size)

35
Tanks Under Trees Radar Sensor

• Concept Use radar at different frequencies and
  polarizations as multiple modalities
• For each modality, already have good para-
  metrized models for vehicles and canopies
• Combine these using previous sequential detection
  and sensor management algorithm to be developed
  as part of this research

36
Evaluation of Resulting Algorithms

• UM Radiation Lab has a number of scattering
  models for vehicles and canopies
• Permits realistic testing of algorithms
• Compute ROC curves for various choices of
  sensors, sensor type, model dimension, noise
• Figures-of-merit powerPrdetection at fixed
  level of significance area under ROC curve

37
Summary

• Sequential detection and classification
• Sensor scheduling and management
• Physics-based models with dimensionality reduced
  using functional analysis
• Vehicle and canopy scattering models already at
  UM permit test evaluations