Related Experiment Video
Updated: Jul 16, 2026
08:16
Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
Published on: October 24, 2025
High-Definition Map-Based Autonomous Vehicle Localization Using LiDAR Point Cloud Similarity Metrics: A Comparative
Sai S Reddy1, Luis G Jaimes1, Onur Toker2
1Department of Computer Science, Florida Polytechnic University, Lakeland, FL 33805, USA.
Sensors (Basel, Switzerland)
|July 15, 2026
Summary
This study compares LiDAR point cloud similarity metrics for autonomous vehicle localization. Procrustes alignment offers the best balance of accuracy and speed for reliable navigation in GPS-denied environments.
Area of Science:
- Robotics and Autonomous Systems
- Computer Vision
- Geospatial Navigation
Background:
- Accurate localization is crucial for autonomous vehicle (AV) navigation, especially where GPS is unreliable.
- Existing LiDAR-based point cloud similarity metrics for high-definition (HD) map localization lack systematic comparison.
- A unified framework is needed to evaluate distinct metric families under identical real-world conditions.
Purpose of the Study:
- To conduct an offline comparative study of three distinct LiDAR point cloud similarity metric families.
- To evaluate metrics within a unified HD map-based localization framework for autonomous vehicles.
- To provide guidance on metric selection for on-road driving scenarios with static environments and yaw-dominant motion.
Main Methods:
- Developed a unified localization framework using a dataset of 19,500 time-synchronized LiDAR scans and GPS data.
- Compared three similarity metrics: Fast Point Feature Histograms (FPFH), Procrustes alignment (SVD-based), and planar projection (2D histogram cross-correlation).
- Evaluated metrics based on similarity score profile (localizability) and per-pair computational cost.
Main Results:
- FPFH offers rich geometric matching but is computationally expensive (~1018s/pair), suitable for offline analysis.
- Procrustes alignment provides smooth score profiles and zero self-similarity baseline at ~2.63s/pair.
- Planar projection yields location-invariant profiles at ~11.6s/pair, balancing invariance and cost.
Conclusions:
- Procrustes alignment demonstrates superior performance in terms of score profile smoothness and computational efficiency for the tested conditions.
- The study provides a reproducible benchmark and guidance for selecting LiDAR similarity metrics in autonomous vehicle localization.
- Further research is needed to bridge the gap between current computational costs and requirements for real-time online deployment.
Related Concept Videos
01:30Types of Global Positioning System Surveys
GPS surveying methods vary in application, accuracy, and data collection techniques, catering to diverse surveying and mapping needs. Static GPS, kinematic GPS, and real-time kinematic (RTK) surveying are widely used. Each technique offers distinct advantages.Static GPS involves placing one receiver at a known reference point and another at the target point. It collects exact positional data by observing multiple satellite ranges over an extended period, achieving centimeter-level accuracy for...
01:30Design Example: Identifying the Locations of Monuments in the Field Using Global Positioning System Device
Surveyors use Global Positioning System (GPS) technology to measure the precise location and elevation of points on Earth. In a recent survey, GPS receivers were used to determine the coordinates and elevations of two park monuments. The process involved careful mission planning, data collection, and correction to ensure accuracy. The survey began with mission planning to identify optimal satellite visibility and minimize Position Dilution of Precision (PDOP). A geodetic control point served as...