Journal of Marine Sciences ›› 2022, Vol. 40 ›› Issue (4): 90-96.DOI: 10.3969j.issn.1001-909X.2022.04.009

Previous Articles    

Comparative research on image fusion methods of GF-2 satellite based on port ship recognition

ZHAO Yizhi1,2, ZHU Haitian3, LI Xiunan1,2, YANG Jingsong1,2, CHEN Peng*1,2   

  1. 1. Second Institute of Oceanography, MNR, Hangzhou 310012, China;
    2. State Key Laboratory of Satellite Ocean Environment Dynamics, Hangzhou 310012, China;
    3. National Satellite Ocean Application Service, Beijing 100081, China
  • Received:2022-03-01 Online:2022-12-15 Published:2023-02-09

Abstract: In satellite remote sensing image recognition, compared with ship recognition in a single marine environment, port ship recognition is more difficult due to the presence of a large number of interference targets such as containers and docks. In order to improve the recognition ability of GF-2 satellite data on port ships, five fusion algorithms, i.e. Intensity Hue Saturation (IHS) Transform, Brovey Transform(BT), ESRI panchromatic sharpening Transform, simple mean Transform and Gram-Schmidt Transform (GS) were used to perform the fusion experiment of panchromatic and multispectral images, and the optimal method applicable to port ship images is selected through qualitative and quantitative evaluation. The results show that GS Transform can increase spatial information while maintaining spectral fidelity, and its mean value, root mean square error, peak signal to noise ratio, and structural similarity are superior to the other four fusion algorithms, with high recognition accuracy for port ships.

Key words: remote sensing, image fusion, port ship, GF-2 satellite data

CLC Number: