Synthetic Aperture Radar Automatic Target Recognition

1
Synthetic Aperture Radar Automatic Target
Recognition

• -Computer Science Department-
• California Polytechnic State University,
• San Luis Obispo
• Alvin Y. Wang and Chia-Huei Yao
• Faculty Advisor Dr. John SaghriProject
  Sponsor Raytheon CompanyContact Personnel Jeff
  Hoffner

2
Agenda

• Introduction
• Automatic Target Recognition
• Synthetic Aperture Radar
• Problem and Proposed Solutions
• Feature Extraction
• Image Matching
• Conclusion

3
Introduction

• Usage of image identification
• Military
• Medical
• SAR images
• MSTAR image database

Courtesy of Sandia National Laboratory
4
Synthetic Aperture Radar

• SAR instruments use pulses of microwaves as an
  active source of illumination
• Benefits
• Independent of light sources
• Capable to see through clouds
• Spatial resolution remains the same no matter
  how far the target area is

5
Automated Target Recognition

• Five Stages
• Feature Extraction Detection
• Feature Enhancement - Discrimination
• Image Matching Classification, Recognition,
  Identification

6
Problem and Proposed Solutions

• Traditional ATR algorithms
• Problem Removal of useful target information
• Solution Multi-feature ATR techniques
• Feature Extraction
• Edge Detection, Topographical Primal Sketch
• Image Matching
• Hausdorff Distance Transform

7
Feature Extraction

• Feature Detection
• Edge Detection Sobel Mask
• Line Detection Laplacian Mask
• Topographical Primal Sketch
• Multiple-feature consideration

8
WaitBefore Feature Detection

• Reject Noise
• The target images are full of noise
• Median filter

9
Edge Detection

• The box provides little clue for identification
• Even worse, the edges are affected by different
  illuminating status and orientation

10
Topographical Primal Sketch

• The light intensity variations on an image are
  caused by an objects surface orientation, its
  reflectance, and characteristics of its lighting
  source
• Based on the variance of light intensity, we can
  classify and group the underlying image into some
  topographical categories

11

• Topographical categories includes peak, pit,
  ridge, ravine, saddle, flat, hillside, etc.
• Based on the location of the topographical
  features, we can reasonably reconstruct the
  original 3D model.

12
Feature Extraction and Distance Transform
Edge
Feature Extraction
Distance Transform
Original Image
Peak
Ridge
13
Image Matching

• Database
• Model templates
• Problems
• Scale
• Rotation
• Partially obstructed images
• Distance Transform

14
Image Matching procedure

• Find contour points of the reference shape and
  obtain their DT
• Obtain contour points of the measured shape
• Compute and superimpose the centroids of the two
  point sets
• Rotate and translate the measured point set with
  respect to the initial pose
• Select those relative positions that yield the
  minimum HD value
• Select the one with the least mean HD.

15
Hausdorff Distance Transform

• h(A,B) max min d(a,b)
• H(A,B) max h(A,B), h(B,A)

16
Hausdorff Distance Illustration
a2
h(A,B)
h(B,A)
H(A,B)
Hausdorff Distance provides a measure of set A
and set Bs proximity it indicates the maximal
distance between any points of A to B.
17
Chamfer Distance Transform

• CDT Provides good approximation to the exact
  Euclidean distance
• Distance Trasform converts a binary image to
  another image in which pixel value is the
  distance from this pixel to the nearest nonzero
  pixel of the binary image.

courtesy of IPAN
18
Image Matching procedure
19
Image Matching procedure

• Find contour points of the reference shape and
  obtain their DT
• Obtain contour points of the measured shape
• Compute and superimpose the centroids of the two
  point sets
• Rotate and translate the measured point set with
  respect to the initial pose
• Select those relative positions that yield the
  minimum HD value
• Select the one with the least mean HD.

20
An image (left) and its distance transform (right)
Test image and Target detected when the contours
are superimposed
courtesy of IPAN
21
Template image
Test image
Target detected
courtesy of Cornell Vision Group
22
Conclusion

• Current Progress and Future Directions
• Feature Extraction
• Feature detection
• TPS
• Image Matching
• Hausdorff Distance Transform
• Testing
• Database
• Actual Matching with test images

23
References

• Image and Pattern Analysis Group
  http//visual.ipan.sztaki.hu/
• Cornell Computer Vision Grouphttp//www.cs.cornel
  l.edu/vision
• Robert M. Haralick, Layne T. Watson, Thomas J.
  Laffey, The Topographic Primal Sketch. The
  international Journal of Robotics Research. Vol.
  2, No. 1, Spring 1983

24
Thank You

• Questions and Comments
• Visit our web page Alvin www.csc.calpoly.edu/ay
  wang
• Huey www.calpoly.edu/cyao