Underground Mapping and Localization Based on Ground-Penetrating Radar

3D object reconstruction based on deep neural networks has gained increasing attention in recent years. However, 3D reconstruction of underground objects to generate point cloud maps remains a challenge. Ground Penetrating Radar (GPR) is one of the most powerful and extensively used tools for detecting and locating underground objects such as plant root systems and pipelines, with its cost-effectiveness and continuously evolving technology. This paper introduces a parabolic signal detection network based on deep convolutional neural networks, utilizing B-scan images from GPR sensors. The detected keypoints can aid in accurately fitting parabolic curves used to interpret the original GPR B-scan images as cross-sections of the object model. Additionally, a multi-task point cloud network was designed to perform both point cloud segmentation and completion simultaneously, filling in sparse point cloud maps. For unknown locations, GPR A-scan data can be used to match corresponding A-scan data in the constructed map, pinpointing the position to verify the accuracy of the map construction by the model. Experimental results demonstrate the effectiveness of our method.

Self-Supervised Depth Estimation Based on Camera Models

Depth estimationn is a critical topic for robotics and vision-related tasks. In monocular depth estimation, in comparison with supervised learning that requires expensive ground truth labeling, self-supervised methods possess great potential due to no labeling cost. However, self-supervised learning still has a large gap with supervised learning in depth estimation performance. Meanwhile, scaling is also a major issue for monocular unsupervised depth estimation, which commonly still needs ground truth scale from GPS, LiDAR, or existing maps to correct. In deep learning era, while existing methods mainly rely on the exploration of image relationships to train the unsupervised neural networks, fundamental information provided by the camera itself has been generally ignored, which can provide extensive supervision information for free, without the need for any extra equipment to provide supervision signals. Utilizing the camera itself's intrinsics and extrinsics, depth information can be calculated for ground regions and regions connecting ground based on physical principles, providing free supervision information without any other sensors. The method is easy to realize and can be a component to enhance the effects of all the unsupervised methods.