A Survey of Spectrogram Track Detection Algorithms

TY - JOUR

T1 - A Survey of Spectrogram Track Detection Algorithms

AU - Lampert, Thomas

AU - O'Keefe, Simon

N1 - Copyright © 2009 Elsevier Ltd. This is an author produced version of the published paper. Uploaded in accordance with the publisher's self-archiving policy.

PY - 2010/2/1

Y1 - 2010/2/1

N2 - The detection of tracks in spectrograms is an important step in remote sensing applications such as the analysis of marine mammal calls and remote sensing data in underwater environments. Recent advances in technology and the abundance of data requires the development of more sensitive detection methods. This problem has attracted researchers' interest from a variety of backgrounds ranging between image processing, signal processing, simulated annealing and Bayesian filtering. Most of the literature is concentrated in three areas: image processing, neural networks, and statistical models such as the Hidden Markov model. There has not been a review paper which describes and critically analyses the application of these key algorithms. This paper presents an extensive survey and an algorithm taxonomy, additionally each algorithm is reviewed according to a set of criteria relating to their success in application. These criteria are defined to be their ability to cope with noise variation over time, track association, high variability in track shape, closely separated tracks, multiple tracks, the birth/death of tracks, low signal-to-noise ratios, that they have no a priori assumption of track shape and that they are computationally cheap. Our analysis concludes that none of these algorithms fully meets these criteria. (C) 2009 Elsevier Ltd. All rights reserved.

AB - The detection of tracks in spectrograms is an important step in remote sensing applications such as the analysis of marine mammal calls and remote sensing data in underwater environments. Recent advances in technology and the abundance of data requires the development of more sensitive detection methods. This problem has attracted researchers' interest from a variety of backgrounds ranging between image processing, signal processing, simulated annealing and Bayesian filtering. Most of the literature is concentrated in three areas: image processing, neural networks, and statistical models such as the Hidden Markov model. There has not been a review paper which describes and critically analyses the application of these key algorithms. This paper presents an extensive survey and an algorithm taxonomy, additionally each algorithm is reviewed according to a set of criteria relating to their success in application. These criteria are defined to be their ability to cope with noise variation over time, track association, high variability in track shape, closely separated tracks, multiple tracks, the birth/death of tracks, low signal-to-noise ratios, that they have no a priori assumption of track shape and that they are computationally cheap. Our analysis concludes that none of these algorithms fully meets these criteria. (C) 2009 Elsevier Ltd. All rights reserved.

KW - Survey

KW - Spectrogram

KW - Acoustic imaging

KW - Acoustic signal detection

KW - Remote sensing

KW - Vibration analysis

KW - Frequency tracking

KW - Frequency Estimation

KW - FREQUENCY LINE TRACKING

KW - HIDDEN MARKOV-MODELS

KW - DISCRETE FOURIER-TRANSFORMS

KW - PROBABILISTIC FUNCTIONS

KW - SPEECH RECOGNITION

KW - ACOUSTIC DETECTION

KW - NEURAL-NETWORKS

KW - SINGLE-TONE

KW - SIGNAL

KW - NOISE

UR - http://www.scopus.com/inward/record.url?scp=70349984523&partnerID=8YFLogxK

U2 - 10.1016/j.apacoust.2009.08.007

DO - 10.1016/j.apacoust.2009.08.007

M3 - Article

VL - 71

SP - 87

EP - 100

JO - Applied Acoustics

JF - Applied Acoustics

IS - 2

ER -