Local search particle filter applied to human-computer interaction

Abstract

This paper presents an hybridization of particle filter and local search algorithms, called local search particle filter (LSPF), and its application to human-computer interaction. The proposed algorithm combines both sequential Monte Carlo (particle filter - PF) and local search methods to achieve an accurate real-time hand tracking. The system allows to control different mouse actions through a reduced set of hand movements and gestures. Hand are segmented using a skin-color model based on explicit RGB region definition. The proposed hybrid tracking method increases the performance of general particle filter. It also improves the quality of the hand tracking task (the standard deviation between hand spatial positions for LSPF is reduced a 75% with respect to the PF algorithm). More precisely, a local search enhances a hand-simulated mouse cursor to smoothly move and thus recognize gestures for performing their associate actions.