ABSTRACT
Based on the low-resolution geostationary optical satellite for maritime surveillance, a complete processing algorithm including ship detection and ship tracking is proposed. Potentially ships are first detected by a constant false alarm rate processing and a morphological filter from the area of water. Image coordinates of ships are then corrected and transformed by using rational polynomial coefficients and high-resolution shoreline database. In the ship-tracking procedure, a convenient motion model based on geographical coordinates is established, and the multiple hypothesis tracking method is used to track ships for further removing false targets and getting motion states of targets ultimately. Our algorithm has been tested using GaoFen-4 (GF-4) satellite image sequences and the automatic identification system messages of ships. The results of the experiment show that the proposed algorithm can effectively detect and track ships in complex scenes and estimate ships’ motion information accurately with the help of a low-resolution geostationary optical satellite.
Acknowledgements
This work was supported by National Natural Science Foundation of China under Grant No.91538201. The authors thank China Centre for Resources Satellite Data and Application for providing GF-4 data sets, and GSHHS database was obtained from https://earth.esa.int/web/nest/downloads/sample-data. In addition, they would like to thank the anonymous reviewers for their valuable and helpful comments and suggestions.
Disclosure statement
No potential conflict of interest was reported by the authors.