LSVL: Large-scale season-invariant visual localization for UAVs

Kinnari, Jouko; Renzulli, Riccardo; Verdoja, Francesco; Kyrki, Ville

doi:10.48550/arxiv.2212.03581

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While in the GNSS denial environment, the Crossview geo-localization method provides an off-line visual localization scheme, so effective image matching algorithms for this application are particularly important [5], [6], [7]. Due to the change of the UAV attitude and the complexity of flight environment, there are geometric deformations, structural differences, and contrast differences between the UAV images and satellite images [8], [9]. This makes it challenging to extract consistent features across these two types of images, resulting in poor accuracy of local feature-based matching methods.…”

Section: Introductionmentioning

confidence: 99%

SeGCN: A Semantic-Aware Graph Convolutional Network for UAV Geo-Localization

Liu,

Wang,

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Cross-view geo-localization via scene matching is crucial in unmanned aerial vehicle (UAV) systems in global navigation satellite system (GNSS) denial environment. However, images in the same scene may undergo geometric distortion and occlusion due to difference in capture viewpoint, time and platform. The existing methods mainly extract consistent features between images by CNNs, while ignoring the semantic distribution and structural information of the objects. Aiming at addressing this issue, we introduce a semantic-aware graph convolutional network (SeGCN). To improve consistent representation of object features from different viewpoints, potential semantic features are inferred via cross-attention of image context. Then, for exploring the structural information of objects, SeGCN performs graph convolution on graph structures constructed from the same semantic features. Finally, the composite features generated by SeGCN and backbone are utilized for scene matching. Comprehensive experiments conducted on the University-1652 and SUES-200 benchmarks establish that the proposed approach attains the highest levels of accuracy in both localization and navigation tasks. Furthermore, we conducted localization simulation experiments on our real UAV datasets, confirming the effectiveness of SeGCN in real world application scenarios.

show abstract