Refining Roadside 4D Radar Vehicle Classification Using Point-Cloud Dispersion
Organizations: Carnegie Mellon University, Pittsburgh, USA · Departamento de Electrónica, Telecomunicações e Informática, Universidade de Aveiro, Portugal · Instituto de Telecomunicações, Universidade de Aveiro, Campus Universitário de Santiago, 3810-193, Aveiro, Portugal · Instituto de Telecomunicações, Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisboa, Portugal
Abstract
Roadside sensing infrastructure is essential for Intelligent Transportation Systems (ITS), but cameras and legacy sensors are limited in range, weather robustness, and depth accuracy. 4D radar complements these modalities by resolving range, azimuth, elevation, and radial velocity under adverse conditions, though its sparse, noisy point clouds make reliable classification difficult. We present a roadside multi-sensor platform combining a 4D radar and stereo depth camera under synchronized acquisition, used to collect a real-world dataset. Our analysis reveals a substantial class-distribution discrepancy between modalities, most notably a strong radar confusion between passenger cars and motorcycles (49.01% and\ 48.60% of the dataset). To address this, we propose a Neyman-Pearson-based binary classifier on the temporally-smoothed 2D positional standard deviation of radar point cloud clusters, reducing classification error from 52.1% to 42.7%. This lightweight and edge-deployable approach improves radar-only classification reliability and lays the foundation for future camera-radar fusion.
Figures & tables
| Field | Description | Unit |
|---|---|---|
| x | Cartesian X coordinate | m |
| y | Cartesian Y coordinate | m |
| z | Cartesian Z coordinate | m |
| range | Measured target distance | m |
| azimuth | Horizontal angle | rad |
| elevation | Vertical angle | rad |
| Field | Description | Unit |
|---|---|---|
| timestamp | Object observation timestamp (UNIX epoch) | s |
| objectID | Unique radar tracking identifier | – |
| classification | Object class label (1=person, 2=bicycle, 4=motorcycle, 5=car, 6=bus, 7=truck) | – |
| confidence | Classification confidence | % |
| x | Local X position in radar frame | m |
| y | Local Y position in radar frame | m |
| Field | Description | Unit |
|---|---|---|
| timestamp | Object observation timestamp (UNIX epoch) | s |
| objectID | Unique camera tracking identifier | – |
| classification | Object class label (1=person, 2=bicycle, 4=motorcycle, 5=car, 6=bus, 7=truck) | – |
| confidence | Classification confidence | % |
| latitude | Global latitude of object | deg |
| longitude | Global longitude of object | deg |
| Object Class | Total object observations | Percentage (%) |
|---|---|---|
| Passenger Car | 12,781 | 49.01 |
| Motorcycle | 12,675 | 48.60 |
| Bicycle | 562 | 2.15 |
| Truck | 63 | 0.24 |
| Total | 26,081 | 100.00 |
| Object Class | Total object observations | Percentage (%) |
|---|---|---|
| Passenger Car | 2,971 | 85.69 |
| Truck | 185 | 5.34 |
| Person | 184 | 5.31 |
| Bicycle | 77 | 2.22 |
| Motorcycle | 40 | 1.15 |
| Total | 3,467 | 100.00 |
Point Cloud Classification
Point cloud classification assigns semantic labels to unordered 3D point sets using their geometry, features, and spatial relationships.
See all 45 papers