Target tracking based on particle filter algorithm with multiple cues fusion

A robust tracking algorithm based on the particle filter with multi-cue adaptive fusion is proposed which can overcome the shortcoming of single visual cue in complex environments. The color and the texture based on the discrete wavelet transform (DWT) are used to describe the tracking target. The weights are adaptively adjusted using the democratic integration according to the current tracking situations, which increases the reliability of observation and improves the robustness of observation model. Due to the use of reliable cues for tracking, the shortcoming of single cue in complex scenes is improved. Meanwhile, the noise variance of each cue is updating to increase the discrimination of each cue. During designing particle filter based tracking algorithm, the likelihood model is constructed depending on adaptive cue fusion mechanism, thus enhancing the robustness of tracking algorithm. The experiments show that the result of better tracking are obtained in circumstances that the target is arbitrarily moving or rotating, partially or completely occlusion, as well as the light changes. When the target with similar color appears, the tracking algorithm with the texture model can distinguish the target with the background.