DocumentCode
231901
Title
Small surface targets detection based on omnidirectional sea-sky-line extraction
Author
Su Li ; Yin Yisong ; Liu Zhilin
Author_Institution
Coll. of Autom., Harbin Eng. Univ., Harbin, China
fYear
2014
fDate
28-30 July 2014
Firstpage
4732
Lastpage
4736
Abstract
Omnidirectional vision system has wide application prospects in maritime surveillance applications for its advantages of unified imaging, 360-degree view and rotation invariant. But it has weak support in techniques of target detection. With the complexity of sea-sky background and the specificity of omnidirectional image, this paper is carrying out the small targets detection on the sea based on omnidirectional image sequences. A method for omnidirectional circular sea-sky line extraction is presented based on orientations of the gradient, then an algorithm for small target detection around the sea-sky line area is proposed based on gradient threshold. The result of the experimental shows the efficiency and advantage of the method in this paper.
Keywords
computer vision; gradient methods; image sequences; object detection; circular sea-sky line extraction; gradient threshold; image sequences; maritime surveillance applications; omnidirectional image; omnidirectional vision system; small surface targets detection; Algorithm design and analysis; Automation; Educational institutions; Electronic mail; Object detection; Pattern recognition; Sea surface; omnidirectional image; sea-sky-line extraction; small targets detection;
fLanguage
English
Publisher
ieee
Conference_Titel
Control Conference (CCC), 2014 33rd Chinese
Conference_Location
Nanjing
Type
conf
DOI
10.1109/ChiCC.2014.6895738
Filename
6895738
Link To Document