The aim of study is to show that the minimum distance estimator is consistent and asymptotically normal with the usual √n rate of convergence for the intensty function of the process Poisson which have a particularty form. We consider the problem of estimation of a multi-dimensional parameter θ_0=(ω^0_1,...,ω^0_d ,γ^0_1,...,γ^0_d). We suppose that the unknown parameter is 2d dimensional and the intensity function of the process is smooth the first d components and discontinuous the others d components of this parameter.