Loading…

A Multi-scale Piecewise-Linear Feature Detector for Spectrogram Tracks

Reliable feature detection is a prerequisite to higher level decisions regarding image content. In the domain of spectrogram track detection and classification, the detection problem is compounded by low signal-to-noise ratios and high variation in track appearance. Evaluation of standard feature de...

Full description

Saved in:
Bibliographic Details
Main Authors: Lampert, T.A., Pears, N.E., O'Keefe, S.E.M.
Format: Conference Proceeding
Language:English
Subjects:
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 335
container_issue
container_start_page 330
container_title
container_volume
creator Lampert, T.A.
Pears, N.E.
O'Keefe, S.E.M.
description Reliable feature detection is a prerequisite to higher level decisions regarding image content. In the domain of spectrogram track detection and classification, the detection problem is compounded by low signal-to-noise ratios and high variation in track appearance. Evaluation of standard feature detection methods in the literature is essential to determine their strengths and weaknesses in this domain. With this knowledge, improved detection strategies can be developed. This paper presents a comparison of line detectors and a novel, multi-scale, linear feature detector able to detect tracks of varying gradients. We outline improvements to the multi-scale search strategies which reduce run-time costs. It is shown that the Equal Error Rates of existing methods are high, highlighting the need for research into novel detectors. Results demonstrate that the proposed method offers an improvement in detection rates when compared to other, state of the art, methods whilst keeping false positive rates low. It is also shown that a multi-scale implementation offers an improvement over fixed scale implementations.
doi_str_mv 10.1109/AVSS.2009.84
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5279751</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5279751</ieee_id><sourcerecordid>5279751</sourcerecordid><originalsourceid>FETCH-LOGICAL-i213t-23434eaa7b41b27445ae7342b6179d11a20e0833a58210e952991023fb12729d3</originalsourceid><addsrcrecordid>eNotjFFLwzAURiMiqLNvvvnSP9Cae5MsuY9l2ilUFDp9HWl3K9HOjaRD_PcO9IPDOU-fENcgSwBJt9Vb25YoJZVOn4hLaedklAVHpyIj60Cj1toa485FltKHPE4bdGQvRF3lT4dxCkXq_cj5S-Cev0Pioglf7GNes58OkfM7nrifdjEfjrT7Y8fde_TbfBV9_5muxNngx8TZv2fitb5fLR6K5nn5uKiaIiCoqUCllWbvbaehQ6u18WyVxm4OljYAHiVLp5Q3DkEyGSQCiWroAC3SRs3Ezd9vYOb1Poatjz9rg5asAfULIQ1Jng</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A Multi-scale Piecewise-Linear Feature Detector for Spectrogram Tracks</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Lampert, T.A. ; Pears, N.E. ; O'Keefe, S.E.M.</creator><creatorcontrib>Lampert, T.A. ; Pears, N.E. ; O'Keefe, S.E.M.</creatorcontrib><description>Reliable feature detection is a prerequisite to higher level decisions regarding image content. In the domain of spectrogram track detection and classification, the detection problem is compounded by low signal-to-noise ratios and high variation in track appearance. Evaluation of standard feature detection methods in the literature is essential to determine their strengths and weaknesses in this domain. With this knowledge, improved detection strategies can be developed. This paper presents a comparison of line detectors and a novel, multi-scale, linear feature detector able to detect tracks of varying gradients. We outline improvements to the multi-scale search strategies which reduce run-time costs. It is shown that the Equal Error Rates of existing methods are high, highlighting the need for research into novel detectors. Results demonstrate that the proposed method offers an improvement in detection rates when compared to other, state of the art, methods whilst keeping false positive rates low. It is also shown that a multi-scale implementation offers an improvement over fixed scale implementations.</description><identifier>ISBN: 9781424447558</identifier><identifier>ISBN: 1424447550</identifier><identifier>EISBN: 0769537189</identifier><identifier>EISBN: 9780769537184</identifier><identifier>DOI: 10.1109/AVSS.2009.84</identifier><language>eng</language><publisher>IEEE</publisher><subject>Acoustic signal detection ; Computer science ; Computer vision ; Detectors ; Feature Detector ; Frequency ; Line Detection ; Parametric ; Piecewise linear techniques ; Principal component analysis ; Sonar detection ; Spectrogram ; Track Detection ; Underwater tracking</subject><ispartof>2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance, 2009, p.330-335</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5279751$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5279751$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Lampert, T.A.</creatorcontrib><creatorcontrib>Pears, N.E.</creatorcontrib><creatorcontrib>O'Keefe, S.E.M.</creatorcontrib><title>A Multi-scale Piecewise-Linear Feature Detector for Spectrogram Tracks</title><title>2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance</title><addtitle>AVSS</addtitle><description>Reliable feature detection is a prerequisite to higher level decisions regarding image content. In the domain of spectrogram track detection and classification, the detection problem is compounded by low signal-to-noise ratios and high variation in track appearance. Evaluation of standard feature detection methods in the literature is essential to determine their strengths and weaknesses in this domain. With this knowledge, improved detection strategies can be developed. This paper presents a comparison of line detectors and a novel, multi-scale, linear feature detector able to detect tracks of varying gradients. We outline improvements to the multi-scale search strategies which reduce run-time costs. It is shown that the Equal Error Rates of existing methods are high, highlighting the need for research into novel detectors. Results demonstrate that the proposed method offers an improvement in detection rates when compared to other, state of the art, methods whilst keeping false positive rates low. It is also shown that a multi-scale implementation offers an improvement over fixed scale implementations.</description><subject>Acoustic signal detection</subject><subject>Computer science</subject><subject>Computer vision</subject><subject>Detectors</subject><subject>Feature Detector</subject><subject>Frequency</subject><subject>Line Detection</subject><subject>Parametric</subject><subject>Piecewise linear techniques</subject><subject>Principal component analysis</subject><subject>Sonar detection</subject><subject>Spectrogram</subject><subject>Track Detection</subject><subject>Underwater tracking</subject><isbn>9781424447558</isbn><isbn>1424447550</isbn><isbn>0769537189</isbn><isbn>9780769537184</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2009</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjFFLwzAURiMiqLNvvvnSP9Cae5MsuY9l2ilUFDp9HWl3K9HOjaRD_PcO9IPDOU-fENcgSwBJt9Vb25YoJZVOn4hLaedklAVHpyIj60Cj1toa485FltKHPE4bdGQvRF3lT4dxCkXq_cj5S-Cev0Pioglf7GNes58OkfM7nrifdjEfjrT7Y8fde_TbfBV9_5muxNngx8TZv2fitb5fLR6K5nn5uKiaIiCoqUCllWbvbaehQ6u18WyVxm4OljYAHiVLp5Q3DkEyGSQCiWroAC3SRs3Ezd9vYOb1Poatjz9rg5asAfULIQ1Jng</recordid><startdate>200909</startdate><enddate>200909</enddate><creator>Lampert, T.A.</creator><creator>Pears, N.E.</creator><creator>O'Keefe, S.E.M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200909</creationdate><title>A Multi-scale Piecewise-Linear Feature Detector for Spectrogram Tracks</title><author>Lampert, T.A. ; Pears, N.E. ; O'Keefe, S.E.M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i213t-23434eaa7b41b27445ae7342b6179d11a20e0833a58210e952991023fb12729d3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Acoustic signal detection</topic><topic>Computer science</topic><topic>Computer vision</topic><topic>Detectors</topic><topic>Feature Detector</topic><topic>Frequency</topic><topic>Line Detection</topic><topic>Parametric</topic><topic>Piecewise linear techniques</topic><topic>Principal component analysis</topic><topic>Sonar detection</topic><topic>Spectrogram</topic><topic>Track Detection</topic><topic>Underwater tracking</topic><toplevel>online_resources</toplevel><creatorcontrib>Lampert, T.A.</creatorcontrib><creatorcontrib>Pears, N.E.</creatorcontrib><creatorcontrib>O'Keefe, S.E.M.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Lampert, T.A.</au><au>Pears, N.E.</au><au>O'Keefe, S.E.M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A Multi-scale Piecewise-Linear Feature Detector for Spectrogram Tracks</atitle><btitle>2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance</btitle><stitle>AVSS</stitle><date>2009-09</date><risdate>2009</risdate><spage>330</spage><epage>335</epage><pages>330-335</pages><isbn>9781424447558</isbn><isbn>1424447550</isbn><eisbn>0769537189</eisbn><eisbn>9780769537184</eisbn><abstract>Reliable feature detection is a prerequisite to higher level decisions regarding image content. In the domain of spectrogram track detection and classification, the detection problem is compounded by low signal-to-noise ratios and high variation in track appearance. Evaluation of standard feature detection methods in the literature is essential to determine their strengths and weaknesses in this domain. With this knowledge, improved detection strategies can be developed. This paper presents a comparison of line detectors and a novel, multi-scale, linear feature detector able to detect tracks of varying gradients. We outline improvements to the multi-scale search strategies which reduce run-time costs. It is shown that the Equal Error Rates of existing methods are high, highlighting the need for research into novel detectors. Results demonstrate that the proposed method offers an improvement in detection rates when compared to other, state of the art, methods whilst keeping false positive rates low. It is also shown that a multi-scale implementation offers an improvement over fixed scale implementations.</abstract><pub>IEEE</pub><doi>10.1109/AVSS.2009.84</doi><tpages>6</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9781424447558
ispartof 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance, 2009, p.330-335
issn
language eng
recordid cdi_ieee_primary_5279751
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Acoustic signal detection
Computer science
Computer vision
Detectors
Feature Detector
Frequency
Line Detection
Parametric
Piecewise linear techniques
Principal component analysis
Sonar detection
Spectrogram
Track Detection
Underwater tracking
title A Multi-scale Piecewise-Linear Feature Detector for Spectrogram Tracks
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T20%3A36%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%20Multi-scale%20Piecewise-Linear%20Feature%20Detector%20for%20Spectrogram%20Tracks&rft.btitle=2009%20Sixth%20IEEE%20International%20Conference%20on%20Advanced%20Video%20and%20Signal%20Based%20Surveillance&rft.au=Lampert,%20T.A.&rft.date=2009-09&rft.spage=330&rft.epage=335&rft.pages=330-335&rft.isbn=9781424447558&rft.isbn_list=1424447550&rft_id=info:doi/10.1109/AVSS.2009.84&rft.eisbn=0769537189&rft.eisbn_list=9780769537184&rft_dat=%3Cieee_6IE%3E5279751%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i213t-23434eaa7b41b27445ae7342b6179d11a20e0833a58210e952991023fb12729d3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5279751&rfr_iscdi=true