Method and apparatus for moving object detection using fisher's linear discriminant based radial basis function network

摘要

A method for moving object detection based on a Fisher's Linear Discriminant-based Radial Basis Function Network (FLD-based RBF network) includes the following steps. A sequence of incoming frames of a fixed location delivered over a network are received. A plurality of discriminant patterns are generated from the sequence of incoming frames based on a Fisher's Linear Discriminant (FLD) model. A background model is constructed from the sequence of incoming frames based on a Radial Basis Function (RBF) network model. A current incoming frame is received and divided into a plurality of current incoming blocks. Each of the current incoming blocks is classified as either a background block or a moving object block according to the discriminant patterns. Whether a current incoming pixel of the moving object blocks among the current incoming blocks is a moving object pixel or a background pixel is determined according to the background model.

主权项

1. A moving object detection method based on a Fisher's Linear Discriminant-based Radial Basis Function Network (FLD-based RBF network) comprising:
receiving a sequence of incoming frames of a fixed location delivered over a network; generating a plurality of discriminant patterns from the sequence of incoming frames based on a Fisher's Linear Discriminant (FLD) model having an optimal projection vector, comprising:
dividing each of the incoming frames into a plurality of training blocks and classifying the training blocks into a plurality of classes;calculating a between-class scatter matrix and a within-class scatter matrix according to the training blocks;calculating the optimal projection vector by maximizing the ratio of the within-class scatter matrix and the between-class scatter matrix; andobtaining each of the discriminant patterns according to the optimal projection vector and the corresponding training block; constructing a background model from the sequence of incoming frames based on a Radial Basis Function (RBF) network model, wherein the RBF network model comprises an input layer having a plurality of input layer neurons, a hidden layer having a plurality of hidden layer neurons, and an output layer having an output layer neuron, and wherein there exists a weight between each of the hidden layer neurons and the output layer neuron; receiving a current incoming frame delivered over the network and dividing the current incoming frame into a plurality of current incoming blocks; classifying each of the current incoming blocks as either a background block or a moving object block according to the discriminant patterns generated from the sequence of incoming frames based on the FLD model, comprising:
calculating a projection of each of the current incoming blocks according to the optimal projection vector;calculating a similarity level between the discriminant pattern and the projection of each of the current incoming blocks;determining if the similarity level exceeds the second threshold value;if yes, classifying the current incoming block as the background block; andif no, classifying the current incoming block as the moving object block; and determining whether a current incoming pixel of the moving object blocks among the current incoming blocks is a moving object pixel or a background pixel according to the background model.