Identification of railway subgrade defects based on ground penetrating radar

A recognition method is proposed to solve the problems in subgrade detection with ground penetrating radar, such as massive data, time–frequency and difference in experience. According to the sparsity of subgrade defects in radar images, the sparse representation of railway subgrade defects is studied from the aspects of the time domain, and time–frequency domain with compressive sensing theory. The features of the radar signal are extracted by sparse representation, thus the sampling data are reduced. Based on fuzzy C-means and generalized regression neural network, a rapid recognition of the railway subgrade defects is realized. Experimental results show that the redundancy of data is reduced, and the accuracy of identification is greatly increased.