Schwegmann, Colin PeterKleynhans, WaldoSalmon, Brian Paxton2015-11-232015-11-232015-07Schwegmann, CP, Kleynhans, W & 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, no. 7, pp. 3329-3337.1939-1404 (print)2151-1535 (online)10.1109/JSTARS.2015.2417756http://hdl.handle.net/2263/50580The 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 10-7 .en© 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.Marine technologySimulated annealingSynthetic aperture radar (SAR)Constant false alarm rate (CFAR)Postprint Article