Title :
The sea-sky-line edge detection method based on panoramic images
Author :
Wenkun Bian ; Qidan Zhu
Author_Institution :
Coll. of Autom., Harbin Eng. Univ., Harbin, China
Abstract :
In order to realize automatic ship target detection with panoramic camera in the marine environment, a sea-sky-line extraction algorithm for panoramic image. Firstly, an improved canny edge detection method based on partition adaptive threshold was used. Then after edge thining, the sea-sky-line edge extraction algorithm was proposed based on the longest curve method and the ellipse fitting was performed to get the sea-sky-line elliptic equation. The experimental results prove that this method can effectively detect the sea-sky-line under complex sea-sky background. The success rate can be up to 93% and the time cost is 46ms/frame, which is robust and real-time.
Keywords :
edge detection; elliptic equations; image segmentation; image thinning; object detection; ships; automatic ship target detection; canny edge detection method; edge thinning; ellipse fitting; longest curve method; marine environment; panoramic images; partition adaptive threshold; sea-sky-line edge detection method; sea-sky-line edge extraction algorithm; sea-sky-line elliptic equation; Bismuth; Cameras; Filtering; Fitting; Image edge detection; Partitioning algorithms; adaptive threshold; edge detection; panoramic image; sea-sky-line extraction;
Conference_Titel :
Mechatronics and Automation (ICMA), 2015 IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-7097-1
DOI :
10.1109/ICMA.2015.7237870