In order to solve two key problems in through-the-wall imaging which are ambiguities of wall parameters and real-time imaging simultaneously

a two step imaging procedure is presented in which firstly the wall parameters are estimated by support vector machine and then the targets behind the wall is located and focused by phase shift migration algorithm.The estimated method is introduced emphatically

and the influence of the size

the location

the shape

the number of the targets and the length of the wall

sampling interval

noise on the estimated wall parameters is mainly discussed.The results demonstrate that the method based on SVM(Support Vector Machine) has the advantages of high precision and low computational time.Finally

the performance of two step imaging procedure is tested by a practical case of through-the-wall imaging

the results show that the procedure can realize real-time imaging under unknown wall characteristics

and also a relatively satisfactory image focusing is obtained.