Enhanced Anomaly Detection in GPR Data by Combining Spatial and Dynamic Information

Detecting and classifying subsurface anomalies in urban infrastructure management is crucial and challenging due to the complexity of underground conditions, with ground penetrating radar (GPR) providing essential noninvasive insights. Challenges in GPR data analysis include: acquiring accurately labeled datasets that cover various anomaly categories, and achieving precise localization of these underground anomalies from GPR data. Addressing these limitations, this article introduces the spatial-dynamic-combined (SpaDyn) framework to identify and classify anomalies in GPR B-scan data, which consists of two main components: Anomaly Region Spatial Localization and Dynamic Feature Extraction. Using both normal and unclassified anomalous data, we first construct an abnormal region extractor extended from the Faster-RCNN architecture to determine the spatial coordinates of potential anomalies. Each identified region is then fit using the bidirectional reservoir computing network (BiD-Res), designed with two reservoirs to capture dynamic features in both horizontal and vertical directions, essential for GPR data due to the continuity of subterranean media and electromagnetic waves. The fit readout model from BiD-Res serves as the dynamic feature representation of the original region, thus transforming the identified regions into a size-independent and category-discriminative "dynamic feature space." These dynamic features are then clustered to help ascertain the specific type of each region. Experimental results on real-world datasets validated the effectiveness of SpaDyn, particularly in scenarios where specific information about anomaly categories is unavailable.