Detection and Classification of Pole-like Landmarks for Domain-invariant 3D Point Cloud Map Matching
This work addresses domain-invariant localization for autonomous systems like robots or vehicles, but it is incremental as it builds on existing deep learning and RANSAC techniques.
The paper tackled the problem of improving visual self-localization in 3D point clouds by using pole-like landmarks, which are stable under seasonal changes, and achieved improved localization performance compared to a baseline method as demonstrated on the NCLT dataset.
In 3D point cloud-based visual self-localization, pole landmarks have a great potential as landmarks for accurate and reliable localization due to their long-term stability under seasonal and weather changes. In this study, we aim to explore the use of recently developed deep learning models for pole classification in the context of pole landmark-based self-localization. Specifically, the proposed scheme consists of two main modules: pole map matching and pole class matching. In the former module, local pole map is constructed and its configuration is compared against a precomputed global pole map. An efficient RANSAC map matching is employed to achieve a good tradeoff between computational efficiency and accuracy. In the latter pole class matching module, the local and global poles paired by the RANSAC map-matching are further compared by means of pole attribute class. To this end, a predefined set of pseudo pole classes is learned via k-means clustering in a self-supervised manner. Experiments using publicly available NCLT dataset showed that the pole-like landmark classification method has an improved effect on the visual self-localization system compared with the baseline method.