An intensity-difference-based maritime horizon detection algorithm

The detection of the maritime horizon holds significance in various applications, ranging from navigation to surveillance, yet remains a formidable challenge due to the dynamic nature of the maritime environment. While several methodologies have been proposed by researchers to address this challenge, traditional approaches such as clustering or Hough transform-based methods often suffer from computational inefficiency. In this paper, a novel intensity-difference-based maritime horizon detection algorithm, designed for rapid and robust performance is presented. The method employs a multi-step process beginning with the identification of high intensity-gradient points within each vertical strip composing the image. Subsequently, a statistical reduction technique is applied to determine the candidate points. Finally, a specialized line searching and fitting algorithm is utilized to precisely determine the horizon line. To evaluate the effectiveness of our approach, extensive testing was conducted using the Singapore Maritime Dataset. The results demonstrate low mean absolute percentage error, consistently below 2%, indicating the efficacy and reliability of the proposed algorithm in accurately detecting the maritime horizon even in challenging sea conditions.