# InterLoc: LiDAR-based Intersection Localization using Road Segmentation with Automated Evaluation Method

arXiv: https://arxiv.org/abs/2505.00512 · HTML: https://mlsanity.com/paper/2505.00512/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 33 references that are in the map.
- First posted on arXiv 1 May 2025.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping](https://mlsanity.com/paper/2007.00258/) (2020)
- [Segment Anything Model for Road Network Graph Extraction](https://mlsanity.com/paper/2403.16051/) (2024)
- [Long-term map maintenance pipeline for autonomous vehicles](https://mlsanity.com/paper/2008.12449/) (2020)
- [Model Guided Road Intersection Classification](https://mlsanity.com/paper/2104.12417/) (2021)
- [Intersection Prediction from Single 360deg Image via Deep Detection of Possible Direction of Travel](https://mlsanity.com/paper/2204.04634/) (2022)

## Built on by (most cited first, 1 of 1)

- [InterKey: Cross-modal Intersection Keypoints for Global Localization on OpenStreetMap](https://mlsanity.com/paper/2509.13857/) (2025)

## Abstract (arXiv)

Online localization of road intersections is beneficial for autonomous vehicle localization, mapping and motion planning. Intersections offer strong landmarks for correcting vehicle pose estimation, anchoring new sensor data in up-to-date maps, and guiding vehicle routing in road network graphs. Despite this importance, intersection localization has not been widely studied, with existing methods either ignoring the rich semantic information already computed onboard or relying on scarce, hand-labeled intersection datasets. To close this gap, we present a novel LiDAR-based method for online vehicle-centric intersection localization. We detect the intersection candidates in a bird's eye view (BEV) representation formed by concatenating a sequence of semantic road scans. We then refine these candidates by analyzing the intersecting road branches and adjusting the intersection center point in a least-squares formulation. For evaluation, we introduce an automated pipeline that pairs localized intersection points with OpenStreetMap (OSM) intersection nodes using precise GNSS/INS ground-truth poses. Experiments on the SemanticKITTI dataset show that our method outperforms the latest learning-based baseline in accuracy and reliability. Sensitivity tests demonstrate the method's robustness to challenging segmentation errors, highlighting its applicability in the real world.