© The Institution of Engineering and Technology
A framework for the fusion of computer-aided detection and classification algorithms for side-scan imagery is presented. The framework is based on the Dempster–Shafer theory of evidence, which permits fusion of heterogeneous outputs of target detectors and classifiers. The utilisation of augmented reality for the training and evaluation of the algorithms used over a large test set permits the optimisation of their performance. In addition, this framework is adaptive regarding two aspects. First, it allows for the addition of contextual information to the decision process, giving more importance to the outputs of those algorithms that perform better in particular mission conditions. Secondly, the fusion parameters are optimised on-line to correct for mistakes, which occur while deployed.
References
-
-
1)
-
S. Reed ,
Y.R. Petillot ,
J. Bell
.
An automated approach to the detection and extraction of mine features in sidescan sonar.
IEEE J. Ocean. Eng.
,
1 ,
90 -
105
-
2)
-
R.R. Coifman ,
D.L. Donoho
.
(1995)
Translation-invariant de-noising, in wavelets and statistics, lecture notes in statistics.
-
3)
-
Aridgides, T., Fernandez, M., Dobeck, G.: `Adaptive 3 dimensional range-crossrange-frequency filter processing string for sea mine classification in side-scan sonar imagery', Proc. SPIE, 1997, 3079, p. 111–122.
-
4)
-
E. Coiras ,
Y. Petillot ,
D.M. Lane
.
Multi-resolution 3-D reconstruction from side-scan sonar images.
IEEE Trans. Image Process.
,
2 ,
382 -
390
-
5)
-
Bell, J., Lianantonakis, M.: `Analysis of target scattering using a finite difference time domain model', Proc. Institute of Acoustics Conf. Sonar Transducers and Numerical Modelling, March 2005, 27, Pt. 1.
-
6)
-
Doherty, M.F., Landowski, J.G., Maynard, P.F.: `Side scan sonar object classification algorithms', Proc. 6th Int. Symp. Unmanned Untethered Submersible Technology, 1989, p. 417–424.
-
7)
-
Reed, S.: `Automatic detection and classification models for sidescan sonar imagery', April 2004, PhD, Heriot-Watt University, Edinburgh, UK.
-
8)
-
M. Unser
.
Texture classification and segmentation using wavelet frames.
IEEE Trans. Image Process.
,
11 ,
1549 -
1560
-
9)
-
L. Xu ,
A. Krzyzak ,
C.Y. Suen
.
Methods of combining classifiers and their applications to handwriting recognition.
IEEE Trans. Syst. Man Cybern.
,
3 ,
418 -
435
-
10)
-
E. Coiras ,
P.-Y. Mignotte ,
Y.R. Petillot ,
J. Bell ,
K. Lebart
.
Supervised target detection and classification by training on augmented reality data.
IET Radar Sonar Navig.
,
1 ,
83 -
90
-
11)
-
G. Shafer
.
(1976)
A mathematical theory of evidence.
-
12)
-
Balasubramanian, R., Stevenson, M.: `Pattern recognition for underwater mine detection', Proc. CAD/CAC Conf, November 2001, Halifax, NS, Canada.
-
13)
-
Dobeck, G.J., Hyland, J.C., Smedley, L.: `Automated detection/classification of sea mines in sonar imagery', Proc. SPIE–Int. Society of Optics, 1997, 2079, p. 90–110.
-
14)
-
Ciany, C.M., Zurawski, W.: `Performance of computer aided detection/ computer aided classification and data fusion algorithms for automated detection and classification of underwater mines', CAD/CAC Conf, November 2001, Halifax, Canada.
-
15)
-
Dobeck, G.J.: `Fusing sonar images for mine detection and classification', Proc. SPIE, 1999, vol. 3710, p. 602–614.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-rsn_20070136
Related content
content/journals/10.1049/iet-rsn_20070136
pub_keyword,iet_inspecKeyword,pub_concept
6
6