The Nearest Near Joint Probabilistic Data Association (NNJPDA) is not used directly in multi-sensor multi-target tracking. This paper presents a method of implementing multi-sensor multi-target tracking by combining maximum likelihood estimation with the Nearest Near Joint Probabilistic Data Association (NNJPDA). The maximum likelihood estimation is used to classify the same source observations at one time into the same set, and then NNJPDA is used to implement multi-target tracking. The theoretical analysis and computer simulation show that this algorithm can achieve multi-sensor multi-target tracking perfectly with low calculation load added and higher precision.