Kalman filtering approach to multispectral/hyperspectral image classification

Linear unmixing is a widely used remote sensing image processing technique for subpixel classification and detection where a scene pixel is generally modeled by a linear mixture of spectral signatures of materials present wit hin the pixel. tin approach, called linear unmixing Kalman filtering (LUKF) , is presented which incorporates the concept of linear unmixing into Kalma n filtering so as to achieve signature abundance estimation, subpixel detec tion and classification for remotely sensed images. Zn this case, the linea r mixture model used in linear unmixing is implemented as the measurement e quation in Kalman filtering. The state equation which is required for Kalma n filtering but absent in linear unmixing is then used to model the signatu re abundance. By utilizing these two equations the proposed LUKF not only c an detect abrupt change in various signature abundances within pixels, but also can detect and classify desired target signatures. The performance of effectiveness and robustness of the LUKF is demonstrated through simulated data and real scene images, Satellite Pour l'Observation de la Terra (SPOT) and Hyperspectral Digital Imagery Collection (HYDICE) data.