The Ship Target Detection Based on Sea-Sky-Line

The autonomous target detection of Marine ships plays an important role in both military and civil applications. Marine ship inspection can usually be carried out first by sea-sky-line inspection to reduce image interference information and calculation amount to improve the accuracy and efficiency of ship inspection. In this paper, a sea-sky-line detection method based on a local OTSU segmentation and Hough transform is proposed based on the characteristics of the sea-sky-line. Then the image is segments and some interference information is deleted to preserve the area to be detected. Based on the sea-sky-line detection, the single-stage target detection method is introduced into the ship detection task. The experimental results show that the aid of sea-sky-line reduces certain interference and computation, and optimizes the accuracy and speed of ship target detection.