Ground penetrating radar B-scan image denoising method

Abstract

The invention relates to a ground penetrating radar B-scan image denoising method, which comprises the following steps: step 1, enabling a ground penetrating radar GPR to detect a single background medium area in which a pipeline target is pre-buried on the ground surface, and obtaining Z GPR B-scan images to form a noise-free GPR label data set; 2, training a multi-scale convolution auto-encoder by using each noise-containing GPR data set and the corresponding noise-free GPR label data set, wherein the multi-scale convolution self-encoder comprises an encoder E and a decoder D; and 3, inputting the GPR image to be denoised into the trained multi-scale convolution auto-encoder, outputting the denoised GPR image through encoding and decoding, calculating the signal-to-noise ratio of the denoised GPR image, and verifying the denoising effect of the multi-scale convolution auto-encoder. According to the invention, the noise-containing GPR image under the condition of low signal-to-noise ratio can be effectively denoised.

Description

technical field [0001] The invention belongs to the field of ground-penetrating radar data processing, and specifically discloses a ground-penetrating radar B-scan image denoising method based on a multi-scale convolution self-encoder. Background technique [0002] Ground Penetrating Radar (GPR), as an important technique for underground non-destructive testing, is widely used to study near-surface geophysical structures and detect buried targets; it uses a transmitting antenna to transmit broadband electromagnetic waves to the ground. Scattering occurs when encountering an interface with electromagnetic differences when propagating in the medium. The receiving antenna infers the parameters such as the dielectric properties, spatial position, and structural size of the underground medium and the detection target based on the waveform and delay of the received scattered echo. However, there are often clutter phenomena in the received scattered echo, which seriously affects th...

AI Technical Summary

Problems solved by technology

[0005] In GPR images, commonly used subspace-based denoising methods are singular value decomposition (SVD), principal component analysis (PCA) and independent component analysis (ICA), which utilize various constraints in the cost function Decompose the matrix; the existing research uses the SVD method to decompose the signal, then design the appropriate principal component, and use the PCA method to reconstruct the signal, and realize the PCA-SVD hybrid method for noise reduction, effectively removing the GPR image random noise; recently, Morphological Component Analysis (MCA) was proposed. Morphological Component Analysis has superior performance compared with traditional methods, but it requires prior knowledge for dictionary learning and requires high processing time to remove clutter; therefore it is not suitable for real-time applications

Images