Fleet formation identification and analyzing method based on disposition feature for remote sensing

Abstract

Fleet formation identification in remote sensing is a significant focus in maritime surveillance. However, fleet may occur with different ship dense and noisy data due to the complex background and different satellite resolution, few studies have discussed formation identification considering the limits of sensing and application. This study introduces an effective fleet formation identification and analysis method based on disposition features for remote sensing. We fully consider and analyze detection performance in remote sensing applications, such as false alarms, missed detections, ship position errors and observed ship attitudes. A hierarchical density-based spatial clustering with noise method is introduced to cluster fleet regions. The robust disposition features are designed for various kinds of formations without using training data, enabling discrete remote sensing observations. Our method is robust to ship detection results and has low computational complexity, making it highly suitable for real applications. The advantages of our method were demonstrated through extensive experiments. The experimental results show that the proposed method achieves formation identification with an accuracy over 95% within less than 0.15 s when the ship detection performance changes over a large range, leading to a performance improvement of 5–27% compared with that of other comparative methods.