VLM-Guided and Spatially Consistent Cross-View Matching and Localization of UGVs in UAV-Stitched Map

In Global Navigation Satellite System (GNSS)-denied urban environments, unmanned ground vehicles (UGVs) face significant difficulties in maintaining reliable localization due to occlusion and structural complexity. Unmanned aerial vehicles (UAVs), with their global perspective, provide complementary information for cross-view matching and localization of UGVs. However, robust cross-view matching and localization are hindered by geometric distortions, semantic inconsistencies, and the lack of stable spatial anchors, limiting the effectiveness of conventional methods. To overcome these challenges, we proposed a cross-view matching and localization (CVML) framework that contains two components. The first component is the Vision-Language Model (VLM)-guided and spatially consistent cross-view matching network (VSCM-Net), which integrates two novel attention modules. One is the VLM-guided positional correction module that leverages semantic cues to refine the projected UGV image within the UAV map, and the other is the shape-aware attention module that enforces topological consistency across ground and aerial views. The second component is a ground-to-aerial mapping module that projects cross-view correspondences from the UGV image onto the UAV-stitched map, thereby localizing the capture position of the UGV image and enabling accurate trajectory-level localization and navigation. Extensive experiments on public and self-collected datasets demonstrate that the proposed method achieves superior accuracy, robustness, and real-world applicability compared with state-of-the-art methods in both cross-view image matching and localization.