Orientation-aware ship detection via a rotation feature decoupling supported deep learning approach

Abstract

Ship imaging position plays an important role in visual navigation, and thus significant focuses have been paid to accurately extract ship imaging positions in maritime videos. Previous studies are mainly conducted in the horizontal ship detection manner from maritime image sequences. This can lead to unsatisfied ship detection performance due to that some background pixels maybe wrongly identified as ship contours. To address the issue, we propose a novel rotational you only look once (YOLO) based model (RYM) to accurately yet fast detect ships from maritime images by considering ship rotation angle. The proposed RYM model are designed to detect tilted ships from images with the help of a rotation decoupled (RD) head, attentional mechanism and bidirectional feature network (BiFPN). The experimental results suggested that RYM can obtain satisfied ship detection performance considering that average accuracy reaches 96.7%. The precision and recall indicators are 93.2% and 94.7%, respectively. The proposed framework can be applied into real-time ship detection task due to that the processing speed is 45.6 frames per second (FPS).