Abnormal Maritime Activity Detection in Satellite Image Sequences Using Trajectory Features

Abstract

Maritime security has gained much attention these days because of the frequent interaction between countries with marine borders. Surveillance systems on land are installed on a fixed point, while there is no mounting point for marine surveillance. Fortunately, with the advancement of aerospace technology, the maritime monitoring is possible with continuous satellite image sequences. In this paper, we proposed a complete scheme for maritime surveillance using image sequences on embedded satellite systems, including maritime object detection, tracking, and abnormal activity classification. The recall rate for object detection is 78%. The recall rate for tracking is 91%. The recall rate for anomaly detection is 78%. The FPS is one frame per second on a low power-consuming device installable on a satellite system. The proposed scheme is helpful for the national defense and is labor saving for coast guard affairs.

Maritime Anomaly Detection for Vessel Traffic Services: A Survey

“…Bauw et al further specifies that one-dimensional high-resolution range profiles are used in their study. Highresolution satellite-based image data, which includes seashores, rivers and islands, is tested in [79]. Remarkably, no shore-based image data has been applied to the screened approaches.…”

Detection of Abnormal Vessel Behaviour Based on Probabilistic Directed Graph Model

“…Varlamis et al built a semantic network model and used a probability graph to analyse the abnormal trajectory of ships (Varlamis et al, 2019). Fahn et al proposed a complete scheme for maritime surveillance using image sequences on embedded satellite systems, including maritime object detection, tracking and abnormal activity classification (Fahn et al, 2019). Pitsikalis, in close collaboration with domain experts, developed a library of maritime patterns which can identify different kinds of ships, such as fishing boats, tugboats, etc.…”