Sea-sky-line detection algorithm based on Seam Carving

Sea-sky-line is important reference information for long-range ship detection. At present, the sea-sky-line detection algorithms, such as liner fitting algorithm, weighted information entropy and Hough line detection methods all need large amount of computation to detect the sea-sky-line. A novel sea-sky-line detection method based on Seam Carving was first proposed in this article. Firstly, the gradient amplitude image was calculated, and then dynamic programming searching for the highest energy line was used to extract the sea-sky-line. The experimental results show that the proposed algorithm have the characteristics of high detection accuracy, wide range of applications, low computational complexity and strong real-time.