Statistical characterization and attenuation of vibration effect for continuous asphalt pavement survey using ground-penetrating radar

Abstract

The vibrations from the antenna during ground-penetrating radar (GPR) surveys may introduce unwanted frequency components in the radar data, thus producing noise in the predicted dielectric constant values along the survey distance. Existing statistical methods for vibration effect attenuation require multiple inputs, which is not feasible for real-time processing. This paper characterized the vibration effect and proposed a real-time statistical method for vibration effect attenuation during continuous GPR surveys. Time and frequency domain features were investigated on the dielectric constant values along the survey distance. Results show that the vibration noise is Gaussian-distributed. Window-based-smoothing methods were proposed to remove the vibration effect. The mean prediction error at the highest operating speed (40 km/h) drops from 11.8 % to 2.4 %. The recommended Gaussian fitting window does not require customized input parameters. The processing time is within seconds, which allows real-time and automatic attenuation of the vibration effect.