AN ALGORITHM FOR SEA-SKY LINE DETECTION UNDER VISIBLE SEA IMAGE

• Main Authors: Oleksandr Shmatko, Volodymyr Aleksiyev, Liang Dong
• Format: Article
• Language: English
• Published: National Technical University "Kharkiv Polytechnic Institute" 2018-12-01
• Series: Сучасні інформаційні системи
• Subjects: Sea-sky line; extract the sea-sky line accurately even from low-resolution image; novel horizon detection method for maritime environment
• Online Access: http://ais.khpi.edu.ua/article/view/152829

Subject of research is the process of sea-sky line detection, based on color feature. The purpose of this work is to develop the method is based on color feature as well as textural information. It consists of sea sky region extraction and horizon detection, which is more precise and fast no matter in the sceneries created by camera mounted on board or on shore. The tasks to be solved is: to propose the new linear fitting metric in sea-sky line extraction. The following results were obtained. The proposed linear fitting method was studies. The performance of proposed horizon detection method is estimated by comparison to other 3 state-of-art methods based on 13 challenging testing videos under different circumstances. The 3 methods are: the method based on discriminates and eigenvalues of covariance matrices in RGB space (H-DE); the method adopting probability distribution functions of sea and sky region (H-PDF) and the method by multi-scale cross modal linear feature (MSCM). The video sequences can be classified into two categories: the camera mounted on board and with camera mounted on shore horizon. Conclusion. The proposed linear fitting method can rectify the outlier values. The experimental results on a sequence of test videos demonstrate that the proposed sea-sky line detection method has a higher accuracy and it is more robust and efficient than other existed methods.