Information Assurance in Sensor Networks

Abstract : Detection and tracking of a varying number of people is very essential in surveillance sensor systems. In the real applications, due to various human appearance and confessors, as well as various environment conditions, multiple targets detection and tracking become even more challenging. During this year, our major contributions of multiple targets detection and tracking are as follows: Firstly, we extend the Particle Filter Gaussian Process Dynamical Model (PF-GPDM) to track multiple targets in complex visual environment. With the PF-GPDM, a high-dimensional training target trajectory data set of the observation space is projected to a low-dimensional latent space through Probabilistic Principal Component Analysis (PPCA), which will then be used to classify test object trajectories, predict the next motion state, and provide Gaussian Process dynamical samples for the particle filter.