We introduced a scheme for finding an optimal data association matrix that represents the relationships between the measurements and tracks in multi-target tracking (MIT). We considered the relationships between targets and measurements as Markov Random Field and assumed a priori of the associations as a Gibbs distribution. Based on these assumptions, it was possible to reduce the MAP estimate of the association matrix to the energy minimization problem. After then, we defined an energy function over the measurement space that may incorporate most of the important natural constraints. To find the minimizer of the energy function, we derived a new equation in closed form. By introducing Lagrange multiplier, we derived a compact equation for parameters updating. In this manner, a pair of equations that consist of tracking and parameters updating can track the targets adaptively in a very variable environments. For measurements and targets, this algorithm needs only multiplications for each radar scan. Through the experiments, we analyzed and compared this algorithm with other representative algorithm. The result shows that the proposed method is stable, robust, fast enough for real time computation, as well as more accurate than other method.