GPR Feature Enhancement of Asphalt Pavement Hidden Defects Using Computational-Efficient Image Processing Techniques

Hyperbolic reflection features from ground-penetrating radar (GPR) data have been recognized as essential indicators for detecting hidden defects in the asphalt pavement. Computer vision and deep learning algorithms have been developed to detect and enhance the hyperbolic features of hidden defects. However, migrating existing hyperbolic feature detection methods using raw GPR data results in inaccurate predictions. Pre-processing raw GPR data using straightforward image processing methods could enhance the reflection features for fast and accurate hyperbolic detection during real-time GPR measurements. This study proposed accessible and straightforward image processing methods as GPR data preprocessing steps (such as the Sobel edge detector and histogram equalization) to assist existing computer vision algorithms for reflection feature enhancement during the GPR survey. Field tests were conducted, and several image processing methods with existing standard image processing libraries were applied. The proposed regions of the identified hyperbola signal-to-noise ratio (RIHSNR) were used to quantify the enhancement performance of hyperbolic feature detectability. Applying Sobel edge detection and Otsu's thresholding to GPR data significantly improves detection accuracy and speed: mAP@0.5 rises from 0.65 to 0.85 for Faster R-CNN and from 0.72 to 0.88 for CBAM-YOLOv8 using the proposed computer vision methods as preprocessing steps. At the same time, inference time drops to 30 ms and 25 ms, respectively.