19 December 2013 Sea-land-line extraction using weighted optimum neighborhood algorithm
Author Affiliations +
Proceedings Volume 9045, 2013 International Conference on Optical Instruments and Technology: Optoelectronic Imaging and Processing Technology; 90451M (2013) https://doi.org/10.1117/12.2038018
Event: International Conference on Optical Instruments and Technology (OIT2013), 2013, Beijing, China
Abstract
In the field of automatic target recognition, research on automatic target recognition in water becomes increasingly important due to its value in maritime security and defense. Sea-land-line extraction under complicated sea-land-sky background plays an important role in water surface target recognition. The weighted optimum neighborhood algorithm is proposed by the feature of complicated sea-land-sky background images. Firstly pretreatment operations and Hough transform are taken in the image to find the potential sea-land-lines. There are several false sea-land-lines and a true sealand- line in these sea-land-lines. In the next step, the weighted values of the fitted sea-land lines’ neighborhood are calculated and the fitted line, which has the biggest weighted value, is the correct sea-land-line. The experimental results show that the algorithm can detect the sea-land-line under complicated sea-land-sky background correctly and effectively, and has advantages such as strong robustness, more accurate and high practical value.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jinhui Lan, Zengli Jia, Chunhong Wu, Jun Yang, "Sea-land-line extraction using weighted optimum neighborhood algorithm", Proc. SPIE 9045, 2013 International Conference on Optical Instruments and Technology: Optoelectronic Imaging and Processing Technology, 90451M (19 December 2013); doi: 10.1117/12.2038018; https://doi.org/10.1117/12.2038018
PROCEEDINGS
7 PAGES


SHARE
Back to Top