Stable and reliable autonomous localization technology is fundamental for realizing autonomous driving. Localization systems based on global positioning system (GPS), cameras, LIDAR, etc., can be affected by building occlusion or drastic changes in the environment. These effects can degrade the localization accuracy and even cause the problem of localization failure. Localizing ground-penetrating radar (LGPR) as a new type of localization can rely only on robust subsurface information for autonomous localization. LGPR is mostly a 2D-2D registration process. This paper describes the LGPR as a slice-to-volume registration (SVR) problem and proposes an end-to-end TSVR-Net-based regression localization method. Firstly, the information of different dimensions in 3D data is used to ensure the high discriminative power of the data. Then the attention module is added to the design to make the network pay attention to important information and high discriminative regions while balancing the information weights of different dimensions. Eventually, it can directly regress to predict the current data location on the map. We designed several sets of experiments to verify the method’s effectiveness by a step-by-step analysis. The superiority of the proposed method over the current state-of-the-art LGPR method is also verified on five datasets. The experimental results show that both the deep learning method and the increase in dimensional information can improve the stability of the localization system. The proposed method exhibits excellent localization accuracy and better stability, providing a new concept to realize the stable and reliable real-time localization of ground-penetrating radar images.

Ground penetrating radar (GPR) is one of the most generally used underground sensing equipment, but it is frequently contaminated by clutter and noise during data acquisition, which has a significant impact on the detection performance of buried targets. The purpose of this letter is to present a novel clutter suppression method based on the principal component Gaussian curvature decomposition (PCGCD). First, the GPR B-scan data are divided into different sub-components using principal component analysis (PCA). Then, a Gaussian curvature decomposition (GCD) method is proposed, which can be applied to PCA domain subspaces to recover more target structure information from random noise. The PCGCD method’s performance is evaluated using both numerical simulation and real-world GPR datasets. The visualization and quantitative results demonstrated our method’s superiority in protecting the underground target structure, removing complex random noise, and improving the detection ability of buried targets.

Localizing ground penetrating radar (LGPR) is an emerging place recognition technology based on prior maps, and has received widespread attention in the field of robot localization in challenging environments. However, due to complex geological environments and equipment limitations, the data collected may have missing GPR traces and irregular sampling issues. The missing of map data can reduce the reliability of spatial accuracy, causing the localization results to deviate from the actual location, and affecting localization accuracy. This paper proposes a solution to reconstruct maps by image recovery for offline map production in LGPR tasks to address this issue. We propose a hybrid-driven method that combines the Convolutional Neural Networks (CNN) with the Half-Quadratic Splitting method under the formulation of Maximum A Posteriori (MAP). This hybrid-driven framework offers both the flexibility of the modeling approach and the advantages of learning-based semantic acquisition. To enhance the stability of the reconstructed maps, we develop a low-frequency enhancement module since high-frequency information in GPR image is more susceptible to environmental changes. Besides, a mask guidance module is employed in the iterative process, which ensures the invariance of the original data during the iterative recovery process. Experiments in different missing cases show that the proposed method has the best image recovery results compared to other popular methods, and the map reconstruction based on the recovery generates the highest localization accuracy of LGPR.

As a promising technology for autonomous driving, localizing ground-penetrating radar (LGPR) is a vehicle localization method that relies on prior maps and couples deeply with subsurface features. However, the unique characteristics of GPR data often lead to a significant number of mismatched candidates during localization. Previous learning-based GPR place recognition methods have primarily relied on 2-D convolutional neural networks (CNNs), which struggle to effectively capture critical temporal information, limiting further performance improvements. To address this limitation, we propose a spatial-temporal U-shaped network (STU-Net) that leverages 3-D CNNs to simultaneously extract spatial and temporal features from GPR image sequences. In addition, residual dense blocks (RDBs) are integrated into the network to enable multiscale feature extraction. Extensive experiments conducted on publicly available datasets demonstrate that our STU-Net achieves state-of-the-art performance, outperforming existing methods with significant improvements.

Localizing ground-penetrating radar (LGPR) benefits from deep subsurface coupling, ensuring robustness against surface variations and adverse weather. While LGPR is widely recognized as the complement of existing vehicle localization methods, its reliance on prior maps introduces significant challenges. Channel misalignment during traversal positioning and time-dimension distortion caused by non-uniform platform motion degrade matching accuracy. Furthermore, rain and snow conditions induce subsurface water-content variations that distort ground-penetrating radar (GPR) echoes, further complicating the localization process. To address these issues, we propose a weather-resilient adaptive spatio-temporal mask alignment algorithm for LGPR. The method employs adaptive alignment and dynamic time warping (DTW) strategies to sequentially resolve channel and time-dimension misalignments in GPR sequences, followed by calibration of GPR query sequences. Moreover, a multi-level discrete wavelet transform (MDWT) module enhances low-frequency GPR features while adaptive alignment along the channel dimension refines the signals and significantly improves localization accuracy under rain or snow. Additionally, a local matching DTW algorithm is introduced to perform robust temporal image-sequence alignment. Extensive experiments were conducted on both public LGPR datasets: GROUNDED and self-collected data covering five challenging scenarios. The results demonstrate superior localization accuracy and robustness compared to existing methods.

Ground-penetrating radar (GPR) , as a sensor for mapping and localizing subsurface features, has gained significant attention in robotic localization for complex environments. However, varying weather conditions change the subsurface dielectric constant, which weakens the registration correlation between real-time images and maps, thereby compromising localization stability. We design an image registration framework for localizing ground penetrating radar (LGPR) in multi-weather. Specifically, we first propose an adaptive hyperbolic receptive field that aims to significantly enhance the robust features in the GPR images, while improving both discrimination capability in map and reliability for image registration. Then, an image alignment module is introduced to eliminate the time-delay blurring problem caused by the variation of dielectric constant under multi-weather conditions. The proposed method was evaluated on three distinct datasets (simulated, publicly available, and self-constructed), demonstrating significant improvements in registration and localization performance. The average correlation coefficient on simulated data achieved a enhancement from 0.3796 to 0.7406 compared with baseline, validating the effectiveness of feature enhancement. Furthermore, measured datasets exhibited 15% higher average registration and localization accuracy than baseline. These results demonstrate that the method provides a reliable guarantee for the stable operation of LGPR systems in complex environments. The datasets will be released at: https://github.com/Eazin-bz/dataset_AHFT.git.