Integration of fuzzy theory and particle swarm optimization for high-resolution satellite scene recognition

Select | Print


Li, Linyi; Chen, Yun ORCID ID icon; Xu, Tingbao


2018-06


Journal Article


Progress in Artificial Intelligence


7


2


147-154


With the rapid development of satellite imaging technology, large amounts of satellite images with high spatial resolutions are now available. High-resolution satellite imagery provides rich texture and structure information, which in the meantime poses a great challenge for automatic satellite scene recognition. In this study, a novel integration method of fuzzy theory and particle swarm optimization (IFTPSO) is proposed to achieve an increased accuracy of satellite scene recognition (SSR) in high-resolution satellite imagery. The particle encoding, fitness function and swarm search strategy are designed for IFTPSO-SSR. The IFTPSOSSR method was evaluated using the satellite scenes from QuickBird, IKONOS and ZY-3. IFTPSO-SSR outperformed three traditional recognition methods with the highest recognition accuracy. The parameter sensitivity of IFTPSO-SSR was also discussed. The proposed method of this study can enhance the performance of satellite scene recognition in high-resolution satellite imagery, and thereby advance the research and applications of artificial intelligence and satellite image analysis.


Springer


Artificial Intelligence and Image Processing not elsewhere classified


https://doi.org/10.1007/s13748-017-0139-z


EP178721


Journal article - Refereed


English


Li, Linyi; Chen, Yun; Xu, Tingbao. Integration of fuzzy theory and particle swarm optimization for high-resolution satellite scene recognition. Progress in Artificial Intelligence. 2018; 7(2):147-154.https://doi.org/10.1007/s13748-017-0139-z



Loading citation data...

Citation counts
(Requires subscription to view)