Skip to content

Research at St Andrews

Detection and classification of right whale calls using an ‘edge’ detector operating on a smoothed spectrogram

Research output: Contribution to journalArticle

Open Access permissions

Open

Standard

Detection and classification of right whale calls using an ‘edge’ detector operating on a smoothed spectrogram. / Gillespie, Douglas Michael.

In: Canadian Acoustics, Vol. 32, No. 2, 06.2004, p. 39-47.

Research output: Contribution to journalArticle

Harvard

Gillespie, DM 2004, 'Detection and classification of right whale calls using an ‘edge’ detector operating on a smoothed spectrogram' Canadian Acoustics, vol. 32, no. 2, pp. 39-47.

APA

Gillespie, D. M. (2004). Detection and classification of right whale calls using an ‘edge’ detector operating on a smoothed spectrogram. Canadian Acoustics, 32(2), 39-47.

Vancouver

Gillespie DM. Detection and classification of right whale calls using an ‘edge’ detector operating on a smoothed spectrogram. Canadian Acoustics. 2004 Jun;32(2):39-47.

Author

Gillespie, Douglas Michael. / Detection and classification of right whale calls using an ‘edge’ detector operating on a smoothed spectrogram. In: Canadian Acoustics. 2004 ; Vol. 32, No. 2. pp. 39-47.

Bibtex - Download

@article{7554cfc8114448efbb76a57f9f88754c,
title = "Detection and classification of right whale calls using an ‘edge’ detector operating on a smoothed spectrogram",
abstract = "A detector has been developed which can reliably detect right whale calls and distinguish them from those of other marine mammals and industrial noise. Detection is a two stage process. In the first, the spectrogram is smoothed by convolving it with a Gaussian kernel and the 'outlines' of sounds are extracted using an edge detection algorithm. This allows a number of parameters to be measured for each sound, including duration, bandwidth and details of the frequency contour such as the positions of maximum and minimum frequency. In the second stage, these parameters are used in a classification function in order to determine which sounds are from right whales. The classifier has been tuned by comparing data from a period when large numbers of right whales were known to be in the vicinity of bottom mounted recorders with data collected on days when it was believed, based on ship and aerial surveys, that no right whales were present. Overall, the detection system is capable of picking out a high proportion of right whale calls logged by a human operator, while at the same time working at a false alarm rate of only one or two calls per day, even in the presence of background noise from humpback whales and seismic exploration. Although it is impossible to reduce the false alarm rate for individual calls to zero whilst still maintaining adequate efficiency, by requiring the detection of several calls within a set waiting time, it is possible to reduce false alarm rate to a negligible level.",
author = "Gillespie, {Douglas Michael}",
year = "2004",
month = "6",
language = "English",
volume = "32",
pages = "39--47",
journal = "Canadian Acoustics",
issn = "2291-1391",
publisher = "Canadian Acoustical Association",
number = "2",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Detection and classification of right whale calls using an ‘edge’ detector operating on a smoothed spectrogram

AU - Gillespie, Douglas Michael

PY - 2004/6

Y1 - 2004/6

N2 - A detector has been developed which can reliably detect right whale calls and distinguish them from those of other marine mammals and industrial noise. Detection is a two stage process. In the first, the spectrogram is smoothed by convolving it with a Gaussian kernel and the 'outlines' of sounds are extracted using an edge detection algorithm. This allows a number of parameters to be measured for each sound, including duration, bandwidth and details of the frequency contour such as the positions of maximum and minimum frequency. In the second stage, these parameters are used in a classification function in order to determine which sounds are from right whales. The classifier has been tuned by comparing data from a period when large numbers of right whales were known to be in the vicinity of bottom mounted recorders with data collected on days when it was believed, based on ship and aerial surveys, that no right whales were present. Overall, the detection system is capable of picking out a high proportion of right whale calls logged by a human operator, while at the same time working at a false alarm rate of only one or two calls per day, even in the presence of background noise from humpback whales and seismic exploration. Although it is impossible to reduce the false alarm rate for individual calls to zero whilst still maintaining adequate efficiency, by requiring the detection of several calls within a set waiting time, it is possible to reduce false alarm rate to a negligible level.

AB - A detector has been developed which can reliably detect right whale calls and distinguish them from those of other marine mammals and industrial noise. Detection is a two stage process. In the first, the spectrogram is smoothed by convolving it with a Gaussian kernel and the 'outlines' of sounds are extracted using an edge detection algorithm. This allows a number of parameters to be measured for each sound, including duration, bandwidth and details of the frequency contour such as the positions of maximum and minimum frequency. In the second stage, these parameters are used in a classification function in order to determine which sounds are from right whales. The classifier has been tuned by comparing data from a period when large numbers of right whales were known to be in the vicinity of bottom mounted recorders with data collected on days when it was believed, based on ship and aerial surveys, that no right whales were present. Overall, the detection system is capable of picking out a high proportion of right whale calls logged by a human operator, while at the same time working at a false alarm rate of only one or two calls per day, even in the presence of background noise from humpback whales and seismic exploration. Although it is impossible to reduce the false alarm rate for individual calls to zero whilst still maintaining adequate efficiency, by requiring the detection of several calls within a set waiting time, it is possible to reduce false alarm rate to a negligible level.

UR - http://www.scopus.com/inward/record.url?scp=3142655785&partnerID=8YFLogxK

M3 - Article

VL - 32

SP - 39

EP - 47

JO - Canadian Acoustics

T2 - Canadian Acoustics

JF - Canadian Acoustics

SN - 2291-1391

IS - 2

ER -

Related by author

  1. Automated detection and tracking of marine mammals: a novel sonar tool for monitoring effects of marine industry

    Hastie, G. D., Wu, G-M., Moss, S., Jepp, P., MacAulay, J. D. J., Lee, A., Sparling, C. E., Evers, C. H. M. & Gillespie, D. M., 6 Sep 2019, In : Aquatic Conservation: Marine and Freshwater Ecosystems. 29, S1, p. 119-130

    Research output: Contribution to journalArticle

  2. A review of unmanned vehicles for the detection and monitoring of marine fauna

    Verfuss, U. K., Aniceto, A. S., Harris, D. V., Gillespie, D., Fielding, S., Jiménez, G., Johnston, P., Sinclair, R. R., Sivertsen, A., Solbø, S. A., Storvold, R., Biuw, M. & Wyatt, R., Mar 2019, In : Marine Pollution Bulletin. 140, p. 17-29 13 p.

    Research output: Contribution to journalReview article

Related by journal

  1. Passive acoustic detection and localization of Mesoplodon densirostris (Blainville's beaked whale) vocalizations using distributed bottom-mounted hydrophones in conjunction with a Digital Tag (DTAG) recording

    Ward, J., Morrissey, R., Moretti, D., DiMarzio, N., Jarvis, S., Johnson, M., Tyack, P. & White, C., 1 Mar 2008, In : Canadian Acoustics. 36, 1, p. 60-66 7 p.

    Research output: Contribution to journalArticle

  2. Passive acoustic measurement of dive vocal behavior and group size of Blainville's beaked whale (Mesoplodon densirostris) in the tongue of the ocean (TOTO)

    DiMarzio, N., Moretti, D., Ward, J., Morrissey, R., Jarvis, S., Izzi, A. M., Johnson, M., Tyack, P. & Hansen, A., 1 Mar 2008, In : Canadian Acoustics. 36, 1, p. 166-172 7 p.

    Research output: Contribution to journalArticle

  3. Statistical classification of odontocete clicks

    Gillespie, D. M. & Caillat, M., Mar 2008, In : Canadian Acoustics. 36, 1, p. 20-26

    Research output: Contribution to journalArticle

  4. A remotely-piloted acoustic array for studying sperm whale vocal behaviour

    Schulz, T., Whitehead, H. & Rendell, L. E., Dec 2006, In : Canadian Acoustics. 34, 4, p. 54-55

    Research output: Contribution to journalArticle

ID: 429346