Symbolic analysis of sonar data for underwater target detection

Kushal Mukherjee, Shalabh Gupta, Asok Ray, Shashi Phoha

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

This paper presents a symbolic pattern analysis method for robust feature extraction from sidescan sonar images that are generated from autonomous underwater vehicles (AUVs). The proposed data-driven algorithm, built upon the concepts of symbolic dynamics and automata theory, is used for detection of mines and mine-like objects in the undersea environment. This real-time algorithm is based on symbolization of the data space via coarse graining, i.e., partitioning of the two-dimensional sonar images. The statistical information, in terms of stochastic matrices that serve as features, is extracted from the symbolized images by construction of probabilistic finite state automata. A binary classifier is designed for discrimination of detected objects into mine-like and nonmine-like categories. The pattern analysis algorithm has been validated on sonar images generated in the exploration phase of a mine hunting operation; these data have been provided by the Naval Surface Warfare Center. The algorithm is formulated for real-time execution on limited-memory commercial-of-the-shelf platforms and is capable of detecting objects on the seabed-bottom.

Original languageEnglish (US)
Article number5766777
Pages (from-to)219-230
Number of pages12
JournalIEEE Journal of Oceanic Engineering
Volume36
Issue number2
DOIs
StatePublished - Apr 1 2011

Fingerprint

Sonar
Target tracking
Automata theory
Autonomous underwater vehicles
Military operations
Finite automata
Feature extraction
Classifiers
Data storage equipment

All Science Journal Classification (ASJC) codes

  • Ocean Engineering
  • Mechanical Engineering
  • Electrical and Electronic Engineering

Cite this

@article{c1aad8d2da8b44149bc76c077eb8f558,
title = "Symbolic analysis of sonar data for underwater target detection",
abstract = "This paper presents a symbolic pattern analysis method for robust feature extraction from sidescan sonar images that are generated from autonomous underwater vehicles (AUVs). The proposed data-driven algorithm, built upon the concepts of symbolic dynamics and automata theory, is used for detection of mines and mine-like objects in the undersea environment. This real-time algorithm is based on symbolization of the data space via coarse graining, i.e., partitioning of the two-dimensional sonar images. The statistical information, in terms of stochastic matrices that serve as features, is extracted from the symbolized images by construction of probabilistic finite state automata. A binary classifier is designed for discrimination of detected objects into mine-like and nonmine-like categories. The pattern analysis algorithm has been validated on sonar images generated in the exploration phase of a mine hunting operation; these data have been provided by the Naval Surface Warfare Center. The algorithm is formulated for real-time execution on limited-memory commercial-of-the-shelf platforms and is capable of detecting objects on the seabed-bottom.",
author = "Kushal Mukherjee and Shalabh Gupta and Asok Ray and Shashi Phoha",
year = "2011",
month = "4",
day = "1",
doi = "10.1109/JOE.2011.2122590",
language = "English (US)",
volume = "36",
pages = "219--230",
journal = "IEEE Journal of Oceanic Engineering",
issn = "0364-9059",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

Symbolic analysis of sonar data for underwater target detection. / Mukherjee, Kushal; Gupta, Shalabh; Ray, Asok; Phoha, Shashi.

In: IEEE Journal of Oceanic Engineering, Vol. 36, No. 2, 5766777, 01.04.2011, p. 219-230.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Symbolic analysis of sonar data for underwater target detection

AU - Mukherjee, Kushal

AU - Gupta, Shalabh

AU - Ray, Asok

AU - Phoha, Shashi

PY - 2011/4/1

Y1 - 2011/4/1

N2 - This paper presents a symbolic pattern analysis method for robust feature extraction from sidescan sonar images that are generated from autonomous underwater vehicles (AUVs). The proposed data-driven algorithm, built upon the concepts of symbolic dynamics and automata theory, is used for detection of mines and mine-like objects in the undersea environment. This real-time algorithm is based on symbolization of the data space via coarse graining, i.e., partitioning of the two-dimensional sonar images. The statistical information, in terms of stochastic matrices that serve as features, is extracted from the symbolized images by construction of probabilistic finite state automata. A binary classifier is designed for discrimination of detected objects into mine-like and nonmine-like categories. The pattern analysis algorithm has been validated on sonar images generated in the exploration phase of a mine hunting operation; these data have been provided by the Naval Surface Warfare Center. The algorithm is formulated for real-time execution on limited-memory commercial-of-the-shelf platforms and is capable of detecting objects on the seabed-bottom.

AB - This paper presents a symbolic pattern analysis method for robust feature extraction from sidescan sonar images that are generated from autonomous underwater vehicles (AUVs). The proposed data-driven algorithm, built upon the concepts of symbolic dynamics and automata theory, is used for detection of mines and mine-like objects in the undersea environment. This real-time algorithm is based on symbolization of the data space via coarse graining, i.e., partitioning of the two-dimensional sonar images. The statistical information, in terms of stochastic matrices that serve as features, is extracted from the symbolized images by construction of probabilistic finite state automata. A binary classifier is designed for discrimination of detected objects into mine-like and nonmine-like categories. The pattern analysis algorithm has been validated on sonar images generated in the exploration phase of a mine hunting operation; these data have been provided by the Naval Surface Warfare Center. The algorithm is formulated for real-time execution on limited-memory commercial-of-the-shelf platforms and is capable of detecting objects on the seabed-bottom.

UR - http://www.scopus.com/inward/record.url?scp=79957821398&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79957821398&partnerID=8YFLogxK

U2 - 10.1109/JOE.2011.2122590

DO - 10.1109/JOE.2011.2122590

M3 - Article

VL - 36

SP - 219

EP - 230

JO - IEEE Journal of Oceanic Engineering

JF - IEEE Journal of Oceanic Engineering

SN - 0364-9059

IS - 2

M1 - 5766777

ER -