Title :
A new algorithm for ship centerline extraction in ISAR image
Author :
Lin-Lin, Du ; Yu-Lin, Xin ; Zeng-Ping, Chen
Author_Institution :
ATR Key Lab., Nat. Univ. of Defense Technol., Changsha, China
Abstract :
The centerline is an important feature in ISAR image features. In this paper, a new ship centerline extraction algorithm is presented. In the improved algorithm, the width character is used in the extraction of the ship centerline, and the line detection in normal centerline detection methods is replaced by line group detection. After finding the ship width and angle, the centerline position can be defined. The simulation results show that the estimation of ship centerline with this algorithm can reach higher precision than that of least-squares method and the projection method.
Keywords :
Hough transforms; feature extraction; image retrieval; ships; synthetic aperture radar; Hough transform; ISAR image; least-squares method; line group detection; projection method; ship centerline extraction; Character recognition; Data mining; High-resolution imaging; Image recognition; Linearity; Marine vehicles; Scattering; Shape; Hough transform; centerline; least-square method; projection;
Conference_Titel :
Advanced Computer Control (ICACC), 2010 2nd International Conference on
Conference_Location :
Shenyang
Print_ISBN :
978-1-4244-5845-5
DOI :
10.1109/ICACC.2010.5486687
