In actual particle filter tracking,the appearance change of objects t ends to be very changeful.To address this problem,an adaptive object tracking algorithm based on three-dimen sional on-line appearance model is presented. It describes objects by spatial and temporal domains and constructs object′s th ree-dimensional appearance model.Indicating object appearance changes over time by multiple linear space elements,it impleme nts the on-line incremental update of models.Based on the tracking mechanism of particle filter,it estimates and we ights each individual element cue online and tracks real-time adaptive moving t argets.Three-dimensional online appeara nce model and online tracking mechanism make the distinguish ability improved between the object and backgrou nd.Therefore,it ensures the stability of the tracking algorithm when the object appearance changes.Experimental results show that the proposed tracking method could accurately track the moving object on a variety o f challenging sequences,and it demonstrates better stability compared with related algorithms,while the target apperance presents various complex changes.