Kalman Filtering and Neural Networks - Chapter 3: LEARNING SHAPE AND MOTION FROM IMAGE SEQUENCES
Kalman Filtering and Neural Networks - Chapter 3: LEARNING SHAPE AND MOTION FROM IMAGE SEQUENCES
In Chapter 2, Puskorius and Feldkamp described a procedure for the supervised training of a recurrent multilayer perceptron – the nodedecoupled extended Kalman filter (NDEKF) algorithm. We now use this model to deal with high-dimensional signals: moving visual images. Many complexities arise in visual processing that are not present in onedimensional prediction problems: the scene may be cluttered with backKalman Filtering and Neural Network