Geo-localization has been widely applied as an important technique to get the longitude and latitude for unmanned aerial vehicle (UAV) navigation in outdoor flight. Due to the possible interference and blocking of GPS signals, the method based on image retrieval, which is less likely to be interfered with, has received extensive attention in recent years. The geo-localization of UAVs and satellites can be achieved by querying pre-obtained satellite images with GPS-tagged and drone images from different perspectives. In this paper, an image transformation technique is used to extract cross-view geo-localization information from UAVs and satellites. A single-stage training method in UAV and satellite geo-localization is first proposed, which simultaneously realizes cross-view feature extraction and image retrieval, and achieves higher accuracy than existing multi-stage training techniques. A novel piecewise soft-margin triplet loss function is designed to avoid model parameters being trapped in suboptimal sets caused by the lack of constraint on positive and negative samples. The results illustrate that the proposed loss function enhances image retrieval accuracy and realizes a better convergence. Moreover, a data augmentation method for satellite images is proposed to overcome the disproportionate numbers of image samples. On the benchmark University-1652, the proposed method achieves the state-of-the-art result with a 6.67% improvement in recall rate (R@1) and 6.13% in average precision (AP). All codes will be publicized to promote reproducibility.

This paper introduces the design and implementation of MS-Mapper, a LiDAR mapping system incorporating a mechanical structure based on a step motor and steering gear. The hardware configuration of MS-Mapper allows for adjustable vertical and horizontal orientations of the LiDAR sensor. The MS-Mapper has two configurations during the mapping process: stationary mapping (S-mapping), which is dedicated to generating detailed point cloud maps and providing pose drift correction. mobile mapping (M-mapping), which is utilized for completing map cavities and ensuring comprehensive coverage mapping. This dual-configuration approach employed by MS-Mapper significantly enhances pose estimation accuracy, particularly in challenging environments such as lengthy corridors. To further improve pose estimation accuracy, we propose a residual selection-based bundle adjustment algorithm. Additionally, we propose a dynamic Gaussian Mixture Model (GMM) tree map representation, which is designed to accommodate dynamic growth. This representation effectively reduces the number of redundant Gaussian models, and minimizes data association costs compared to utilizing a dense point cloud. Furthermore, a configuration selection algorithm is proposed to detect pose estimation degeneration and determine optimal opportunities for switching configurations. In summary, the MS-Mapper system amalgamates the strengths of traditional Terrestrial Laser Scanner (TLS) and LiDAR SLAM approaches. MS-Mapper provides a robust solution for achieving accurate mapping results.

In this paper, we introduce a novel approach to fine-grained cross-view geo-localization. Our method aligns a warped ground image with a corresponding GPS-tagged satellite image covering the same area using homography estimation. We first employ a differentiable spherical transform, adhering to geometric principles, to accurately align the perspective of the ground image with the satellite map. This transformation effectively places ground and aerial images in the same view and on the same plane, reducing the task to an image alignment problem. To address challenges such as occlusion, small overlapping range, and seasonal variations, we propose a robust correlation-aware homography estimator to align similar parts of the transformed ground image with the satellite image. Our method achieves sub-pixel resolution and meter-level GPS accuracy by mapping the center point of the transformed ground image to the satellite image using a homography matrix and determining the orientation of the ground camera using a point above the central axis. Operating at a speed of 30 FPS, our method outperforms state-of-the-art techniques, reducing the mean metric localization error by 21.3% and 32.4% in same-area and cross-area generalization tasks on the VIGOR benchmark, respectively, and by 34.4% on the KITTI benchmark in same-area evaluation.