A Model-Based Approach to the Detection and Classification of Mines in Side-scan Sonar

S.Reed, Y.Petillot, J.Bell

Contents

Why Use Unsupervised Techniques?
Our Proposed CAD/CAC algorithm.
The Sonar Process.
Automated Object Detection.
Extraction of Object Features.
Automated Object Classification.
Future Research.
Conclusions.

Unsupervised Techniques

Rapid Advances in AUV Technology.
On-board analysis now required.
Large amounts of data quickly available for analysis.

Unsupervised Techniques

Future automated systems will require all available information (navigation data, image processing models .etc.) to be fused.

CAD/CAC Proposal

The Sonar Process

Sonar images represent the time of flight of the sound rather than distance.
Objects appear as a highlight/shadow pair in the sonar image.

The Detection Model

A Markov Random Field(MRF) model framework is used.
MRF models operate well on noisy images.
A priori information can be easily incorporated.

Basic MRF Theory

A pixel’s class is determined by 2 terms:
- The probability of being drawn from each classes distribution.
- The classes of its neighbouring pixels.

Incorporating A Priori Info

Object-highlight regions appear as small, dense clusters.
Most highlight regions have an accompanying shadow region.

Initial Detection Results

Initial Results Good.
Model sometimes detects false alarms due to clutter such as the surface return – requires more analysis!

Object Feature Extraction

The object’s shadow is often extracted for classification.
The shadow region is generally more reliable than the object’s highlight region for classification.
Most shadow extraction models operate well on flat seafloors but give poor results on complex seafloors.

The CSS Model

2 Statistical Snakes segment the mugshot image into 3 regions : object-highlight, object-shadow and background.

CSS Results

The Combined Model

Objects detected by MRF model are put through the CSS model.
The CSS snakes are initialised using the label field from the detection result. This ensures a confident initialisation each time.
The CSS can detect MANY of the false alarms. False alarms without 3 distinct regions ensure the snakes rapidly expand, identifying the detection as a false alarm.
Navigation info is also used to produce height information which can also remove false alarms.

The combined detection/CSS model was run on 200 BP’02 data files containing 70 objects.
80% of the objects where detected and features extracted(for classification).
0.275 false alarms per image.
The surface return resulted in some of the objects not being detected. Dealing with this would produce a detection rate of ~ 91%.

Object Classification

The extracted object’s shadow can be used for classification.
We extend the classic mine/not-mine classification to provide shape and dimension information.
The non-linear nature of the shadow-forming process ensures finding relevant invariant features is difficult.

Modelling the Sonar Process

Mines can be approximated as simple shapes – cylinders, spheres and truncated cones.
Using Nav data to slant-range correct, we can generate synthetic shadows under the same sonar conditions as the object was detected.
Simple line-of-sight sonar simulator. Very fast.

Comparing the Shadows

Iterative Technique is required to find best fit. Parameter space limited by considering highlight and shadow length.
Synthetic and real shadow compared using the Hausdorff Distance.
It measures the mismatch of the 2 shapes.

Incorporating Knowledge

As the technique is model-based, information on likely mine dimensions can be incorporated.
Limited information from the highlight region can also be used to distinguish between the tested classes.
We obtain an overall membership function for each class.

The Classification Decision

A decision could be made by simply defining a ‘Positive Classification Threshold’. This is a ‘hard’ decision and non-changeable.
The ‘lawnmower’ nature of Sidescan surveys ensures the same object is often viewed multiple times. The model should ideally be capable of multi-view classification.
We use DEMPSTER-SHAFER theory.

Mono-view Results

Dempster-Shafer allocates a BELIEF to each class.
Unlike Bayesian or Fuzzy methods, D-S theory can also consider union of classes.

Automated Detection/Feature Extraction model has been developed and tested on a large amount of data. Good Results obtained, improvements expected when surface returns removed.
Classification model uses a simple sonar simulator and Dempster-Shafer theory to classify the objects. Extends mine/not-mine classification to provide shape and size information.
Future research is focusing on texture segmentation to complement the current work.

Acknowledgements

We would like to thank the following institutions for
their support and for providing data:
DRDC–Atlantic, Canada
Saclant Centre, Italy
GESMA, France