Cross-View Localization via Redundant Sliced Observations and A-Contrario Validation
This addresses reliability assessment in cross-view localization for smart vehicles, offering a novel validation approach that is incremental to existing methods.
The paper tackles the problem of unreliable single-observation outputs in cross-view localization for smart vehicles in GNSS-denied environments by introducing Slice-Loc, a method that creates redundant observations from image slices and validates them using a-contrario reliability validation. The result is a reduction in mean localization error from 4.47 m to 1.86 m and mean orientation error from 3.42° to 1.24° on cross-city tests, with errors exceeding 10 m dropping below 3% after filtering.
Cross-view localization (CVL) matches ground-level images with aerial references to determine the geo-position of a camera, enabling smart vehicles to self-localize offline in GNSS-denied environments. However, most CVL methods output only a single observation, the camera pose, and lack the redundant observations required by surveying principles, making it challenging to assess localization reliability through the mutual validation of observational data. To tackle this, we introduce Slice-Loc, a two-stage method featuring an a-contrario reliability validation for CVL. Instead of using the query image as a single input, Slice-Loc divides it into sub-images and estimates the 3-DoF pose for each slice, creating redundant and independent observations. Then, a geometric rigidity formula is proposed to filter out the erroneous 3-DoF poses, and the inliers are merged to generate the final camera pose. Furthermore, we propose a model that quantifies the meaningfulness of localization by estimating the number of false alarms (NFA), according to the distribution of the locations of the sliced images. By eliminating gross errors, Slice-Loc boosts localization accuracy and effectively detects failures. After filtering out mislocalizations, Slice-Loc reduces the proportion of errors exceeding 10 m to under 3\%. In cross-city tests on the DReSS dataset, Slice-Loc cuts the mean localization error from 4.47 m to 1.86 m and the mean orientation error from $\mathbf{3.42^{\circ}}$ to $\mathbf{1.24^{\circ}}$, outperforming state-of-the-art methods. Code and dataset will be available at: https://github.com/bnothing/Slice-Loc.