Nonlinear Joint Fusion and Detection of Mines Using Multisensor Data

Report No. ARL-TN-314
Authors: Nasser M. Nasrabadi
Date/Pages: May 2008; 18 pages
Abstract: This report describes a new nonlinear joint fusion and anomaly detection technique for mine detection applications using two different types of sensor data (synthetic aperture radar [SAR] and hyperspectral sensor [HS] data). A well-known anomaly detector called the RX algorithm is first extended to perform fusion and detection simultaneously at the pixel level by appropriately concatenating the information from the two sensors. This approach is then extended to its nonlinear version. The nonlinear fusion-detection approach is based on the statistical kernel learning theory which explicitly exploits the higher-order dependencies (nonlinear relationships) between the two types of sensor data through an appropriate kernel. Experimental results for detecting anomalies (mines) in hyperspectral imagery are presented for linear and nonlinear joint fusion and detection for a co-registered SAR and HS imagery. The results show that the nonlinear techniques outperform linear versions.
Distribution: Approved for public release
  Download Report ( 0.976 MBytes )
If you are visually impaired or need a physical copy of this report, please visit and contact DTIC.
 

Last Update / Reviewed: May 1, 2008