30 October 2009 Transfer network learning based remote sensing target recognition
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74950A (2009) https://doi.org/10.1117/12.833583
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
The target recognition accuracy of remote sensing images is not satisfied. The labels of images acquisition and recollecting are difficult and expensive. In order to solve the problem, we introduce transfer learning into Network Boosting algorithm (NB) and propose Transfer Network Learning algorithm (TNL), in which other out-date data are reused to instruct the remote sensing target recognition. TNL is suitable to improve the performance of remote sensing target recognition, in which instances transfer learning is adopted for domain adaptation. The experimental results on the MSTAR SAR data set and remote sensing data set including two-class planes show that the proposed algorithm has better performance and achieves different domains learning.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shuiping Gou, Shuiping Gou, Yuqin Wang, Yuqin Wang, Licheng Jiao, Licheng Jiao, } "Transfer network learning based remote sensing target recognition", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74950A (30 October 2009); doi: 10.1117/12.833583; https://doi.org/10.1117/12.833583


Multi-class open set recognition for SAR imagery
Proceedings of SPIE (May 11 2016)
Machine learning in exploitation
Proceedings of SPIE (May 18 2005)
Feature-based RNN target recognition
Proceedings of SPIE (September 14 1998)
ATR performance of a Rician model for SAR images
Proceedings of SPIE (August 16 2000)
SAR ATR: so what's the problem? An MSTAR perspective
Proceedings of SPIE (August 12 1999)

Back to Top