This paper introduces a new object tracking method

which combines two algorithms working in parallel, and based on

low-level observations (colour and gradient orientation): the Generalised Hough Transform, using a pixel-based descr iption, and

the Particle Filter, using a global descr iption. The object model is

updated by combining information a back-projection map

computed the Generalised Hough Transform, providing

for every pixel the degree to which it may belong to the

object, and the Particle Filter, providing a probability

density on the global object position. The proposed tracker

makes the most of the two algorithms, in terms of robustness to

appearance variation like scaling, rotation, non-rigid deformation

or illumination changes.-This paper introduces a new object tracking method

which combines two algorithms working in parallel, and based on

low-level observations (colour and gradient orientation): the Generalised Hough Transform, using a pixel-based descr iption, and

the Particle Filter, using a global descr iption. The object model is

updated by combining information　a back-projection map

computed　the Generalised Hough Transform, providing

for every pixel the degree to which it may belong to the

object, and　the Particle Filter, providing a probability

density on the global object position. The proposed tracker

makes the most of the two algorithms, in terms of robustness to

appearance variation like scaling, rotation, non-rigid deformation

or illumination changes.