From Data to D3 Model: Adaptive Subsurface Anomaly Detection in GPR Data

Urban development requires meticulous attention to subsurface conditions to ensure the reliable operation of roads and facilities. A ground penetrating radar (GPR) offers a nondestructive solution for subsurface anomaly detection. However, the invisible and variable subsurface environments, combined with limited labeled data, make the detection process challenging. While the "learning in the model space (LMS)" shows efficacy by fitting the data to capture the inherent dynamics and representing the original data with fitted models for further process, it falls short in handling GPR B-scan data due to its unidirectional fitting, static model metric, and manual model adjustment. Addressing these challenges, this article introduces learning in the dual-directional dynamic-captured (D3) model space. We frame the collected GPR B-scan data and fit the GPR data in each frame both horizontally and vertically, encapsulating the dual-directional dynamics within this data frame into a concise D3 model. This D3 model then serves as a representation for this GPR data, mapping the original data from the data space to the D3 model space and enabling learning on the models rather than the raw data. With the proposed parameterized model metric, our method offers adaptability to diverse data scenarios. We further introduce an optimization algorithm that fine-tunes the fitting process and establishes an optimal model metric, resulting in a "category-distinctive" D3 model space. This enables precise anomaly detection and classification within the D3 model space. Experiments on GPR data underline the superiority of our method in real-world applications.