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.
Index Terms—Satellite image analysis, intelligent surveillance, ship detection, abnormal detection, trajectory analysis.
Chin-Shyurng Fahn is with Dept. of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei 10607, Taiwan (e-mail: csfahn@mail.ntust.edu.tw).
Jer Ling, Ming-Yuan Yeh, and Po-Yen Huang are with Dept. of System Engineering, National Space Organization, Hsinchu 30078, Taiwan (e-mail: se01@nspo.narl.org.tw, marco@nspo.narl.org.tw).
Meng-Luen Wu is with Dept. of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei 10607, Taiwan (e-mail: d10015015@mail.ntust.edu.tw).
[PDF]
Cite: Chin-Shyurng Fahn, Jer Ling, Ming-Yuan Yeh, Po-Yen Huang, and Meng-Luen Wu, "Abnormal Maritime Activity Detection in Satellite Image Sequences Using Trajectory Features," International Journal of Future Computer and Communication vol. 8, no.1, pp. 29-33, 2019.
