Traditional target tracking algorithms cannot effectively use the attribute information of the target.Existing radar target tracking algorithms based on PN learning acquires too little target attribute information

so the filtering ability of these algorithms is still insufficient in the more complicated actual environment of clutter. Aiming at this problem

a target tracking filtering algorithm based on multi-attribute support vector machine（SVM）classifier is proposed. On the basis of original PN learning algorithm

the algorithm widens the dimensions of data information obtained by radar system. These data reflect the characteristics of the target and clutter better

which making an improved ability of radar to recognize clutter. The Simulation experiment shows that the proposed algorithm effectively improves the precision of target tracking in a strong clutter environment.