Anomaly Detection Algorithm Based on Nonsubsampled Pyramid Decomposition and Kernel Unsharp Masking for Hyperspectral Image
An anomaly detection algorithm for hyperspectral image (HI) based on nonsubsampled Pyramid decomposition (NSPD) was proposed. Firstly,the HI was decomposed into a series of different scale sub-bands using NSPD;and then using the correlation of neighborhood coefficient of different scale space in a wave-band,the background data was optimally predicted by reducing the anomalous data using the improved kernel unshaip masking filter in different scale of each sub-band. Finally the anomaly targets could be detected by using the RX operator in the feature space. Numerical experiments are conducted on real and synthesized HI data to validate the effectiveness of the proposed algorithm. Compared with the RX algorithm,experimental results show that the proposed algorithm has better detection performance and lower false alarm probability.
hyperspectral image anomaly detection nonsubsampled pyramid decomposition Kernel unshaip Masking
Zhou Huixin Cheng Maolin Qin Hanlin Shen Fumin Lai Rui
School of Technical Physics,Xidian University,Xian,Shaanxi,710071,China School of computer science and technology,Nanjing University of science and technology,Nanjing,Jiang School of Microelectronics Xidian University,Xian,Shaanxi,710071,China
国际会议
西安
英文
1166-1169
2011-12-23（万方平台首次上网日期，不代表论文的发表时间）