Guiding Random Particles by Deterministic Search

Abstract

Among the algorithms developed towards the goal of robust and efficient tracking, two approaches which stand out due to their success are those based on particle filtering and variational approaches. The Bayesian approach led to the development of the particle filter, which performs a random search guided by a stochastic motion model. On the other hand, localising an object can be based on minimising a cost function. This minimum can be found using variational methods. The search paradigms differ in these two methods. One is stochastic and model-driven while the other is deterministic and data-driven. This paper presents a new algorithm to incorporate the strengths of both approaches into one consistent framework. To allow this fusion a smooth, wide likelihood function is constructed, based on a sum-of-squares distance measure and an appropriate sampling scheme is introduced. Based on low-level information this scheme automatically mixes the two methods of search and adapts the computational demands of the algorithm to the difficulty of the problem at hand. The ability to effectively track complex motions without the need for finely tuned motion models is demonstrated.