Moving Ship Detection Method Based on Multi-scale Dual-neighborhood Saliency for GF-4 Satellite Remote Sensing Images br

The GEostationary Orbit(GEO) GF-4 satellite has the ability to observe continuously moving shipsat sea. Ship targets are often weak in the optical remote sensing images of GF-4 satellite, making it difficult todetect directly. By analyzing the wake characteristics of moving ships, a moving ship detection method basedon Multi-scale Dual-neighborhood Saliency Model (MDSM) is proposed. First, the saliency of the image is calculatedbased on MDSM. Then, the position of the moving ship is extracted by adaptive segmentation threshold.Finally, the shape of the candidate target is verified to remove further the false target. Experimental resultsand analysis show that the proposed method can effectively detect multiple moving targets in GF-4 satelliteimages, and has better detection performance compared with the current mainstream visual saliency algorithms