ResearchSpace

Manifold adaptation for constant false alarm rate ship detection in South African oceans

Show simple item record

dc.contributor.author Schwegmann, CP
dc.contributor.author Kleynhans, W
dc.contributor.author Salmon, BP
dc.date.accessioned 2015-11-16T07:14:24Z
dc.date.available 2015-11-16T07:14:24Z
dc.date.issued 2015-04
dc.identifier.citation Schwegmann, CP, Kleynhans, W and Salmon, BP. 2015. Manifold adaptation for constant false alarm rate ship detection in South African oceans. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 8(7), pp 3329 - 3337 en_US
dc.identifier.issn 1939-1404
dc.identifier.uri http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7084591&searchWithin=%22Authors%22:.QT.Schwegmann,%20C.P..QT.&newsearch=true
dc.identifier.uri http://hdl.handle.net/10204/8283
dc.description Copyright: 2015 IEEE. This is a post-print version. The definitive version of the work is published in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing en_US
dc.description.abstract The detection of ships at sea is a difficult task made more so by uncooperative ships, especially when using transponder based ship detection systems. Synthetic Aperture Radar imagery provides a means of observation independent of the ships cooperation and over the years a vast amount of research has gone into the detection of ships using this imagery. One of the most common methods used for ship detection in Synthetic Aperture Radar imagery is the Cell-Averaging Constant False Alarm Rate prescreening method. It uses a scalar threshold value to determine how bright a pixel needs to be in order to be classified as a ship and thus inversely how many false alarms are permitted. This paper presents by a method of converting the scalar threshold into a threshold manifold. The manifold is adjusted using a Simulated Annealing algorithm to optimally fit to information provided by the ship distribution map which is generated from transponder data. By carefully selecting the input solution and threshold boundaries, much of the computational inefficiencies usually associated with Simulated Annealing can be avoided. The proposed method was tested on six ASAR images against five other methods and had a reported detection accuracy of 85:2% with a corresponding false alarm rate of 1.01 x 10(sup-7). en_US
dc.language.iso en en_US
dc.publisher IEEE en_US
dc.relation.ispartofseries Workflow;14954
dc.subject Maritime domain awareness en_US
dc.subject MDA en_US
dc.subject Maritime surveillance en_US
dc.subject Constant False Alarm Rate en_US
dc.subject CFAR en_US
dc.subject Marine technology en_US
dc.subject Simulated annealing en_US
dc.subject Synthetic aperture radar en_US
dc.subject SAR en_US
dc.subject South African oceans en_US
dc.title Manifold adaptation for constant false alarm rate ship detection in South African oceans en_US
dc.type Article en_US
dc.identifier.apacitation Schwegmann, C., Kleynhans, W., & Salmon, B. (2015). Manifold adaptation for constant false alarm rate ship detection in South African oceans. http://hdl.handle.net/10204/8283 en_ZA
dc.identifier.chicagocitation Schwegmann, CP, W Kleynhans, and BP Salmon "Manifold adaptation for constant false alarm rate ship detection in South African oceans." (2015) http://hdl.handle.net/10204/8283 en_ZA
dc.identifier.vancouvercitation Schwegmann C, Kleynhans W, Salmon B. Manifold adaptation for constant false alarm rate ship detection in South African oceans. 2015; http://hdl.handle.net/10204/8283. en_ZA
dc.identifier.ris TY - Article AU - Schwegmann, CP AU - Kleynhans, W AU - Salmon, BP AB - The detection of ships at sea is a difficult task made more so by uncooperative ships, especially when using transponder based ship detection systems. Synthetic Aperture Radar imagery provides a means of observation independent of the ships cooperation and over the years a vast amount of research has gone into the detection of ships using this imagery. One of the most common methods used for ship detection in Synthetic Aperture Radar imagery is the Cell-Averaging Constant False Alarm Rate prescreening method. It uses a scalar threshold value to determine how bright a pixel needs to be in order to be classified as a ship and thus inversely how many false alarms are permitted. This paper presents by a method of converting the scalar threshold into a threshold manifold. The manifold is adjusted using a Simulated Annealing algorithm to optimally fit to information provided by the ship distribution map which is generated from transponder data. By carefully selecting the input solution and threshold boundaries, much of the computational inefficiencies usually associated with Simulated Annealing can be avoided. The proposed method was tested on six ASAR images against five other methods and had a reported detection accuracy of 85:2% with a corresponding false alarm rate of 1.01 x 10(sup-7). DA - 2015-04 DB - ResearchSpace DP - CSIR KW - Maritime domain awareness KW - MDA KW - Maritime surveillance KW - Constant False Alarm Rate KW - CFAR KW - Marine technology KW - Simulated annealing KW - Synthetic aperture radar KW - SAR KW - South African oceans LK - https://researchspace.csir.co.za PY - 2015 SM - 1939-1404 T1 - Manifold adaptation for constant false alarm rate ship detection in South African oceans TI - Manifold adaptation for constant false alarm rate ship detection in South African oceans UR - http://hdl.handle.net/10204/8283 ER - en_ZA


Files in this item

This item appears in the following Collection(s)

Show simple item record