1 of 21

Resolution-Aware Roadside LiDAR Perception and A Real-World Testbed

Arizona State University

Dajiang Suo, Assistant Professor

1

10/09/2025

2 of 21

Background and Motivation

2

Chattanooga City Roadside LiDAR deployment over 120 intersections

Image source: Ouster

Roadside LiDAR studies from Academia

[Li 2022]

[Xu 2020]

3 of 21

Why Resolution Matters�- Tradeoff between Cost and Resolution

3

Cost

Camera

2D Resolution

Performance

3D Resolution

4 of 21

From 2D to 3D (Spatial) Resolution

4

Traffic camera

Roadside LiDAR

Credits to SourceSensors

Credits to Agarwal

Real objects

2D representation

3D representation

5 of 21

Why Resolution Matters�- A Deep Learning Perspective

5

MLP

Preprocessing

Representation & Partitioning

CNN

Feature encoding

Backbone

MLP

Task heads

Results

6 of 21

From 2D to 3D (Spatial) Resolution

6

Traffic camera

Roadside LiDAR

Credits to SourceSensors

Research question: To what extent do sensors that provide 3D spatial resolution (e.g., LiDAR) complement and/or outperform 2D cameras in various roadside sensing tasks?

7 of 21

Resolution Impact on Downstream ITS Tasks

  • Object detection

  • Trajectory tracking and prediction

  • Scene Understanding and decision support for traffic management

7

Credits to Goget.com

Image source: MAG & ADOT

[Toe 2024]

8 of 21

A Real-World Testbed for Studying the Impact of (3D) Spatial Resolution of LiDAR

8

Riggs Rd and S. Dobson Rd at Sun Lakes, AZ

(128/64/16 channels)

9 of 21

Traffic Camera View of the Intersection Testbed

9

10 of 21

(LiDAR) Point Cloud Projection on (Camera) 2D Images

10

16 Channel

128 Channel

64 Channel

11 of 21

LiDAR Resolution and Point Cloud Distribution

11

128 Channel

64 Channel

*He, Y., Cao, P., Suo, D. and Liu, X., 2024. A joint optimization of beam distribution and deployment for roadside LiDAR systems to maximize vehicle perception. IEEE Transactions on Intelligent Vehicles.

12 of 21

LiDAR Resolution and Point Cloud Distribution

12

*He, Y., Cao, P., Suo, D. and Liu, X., 2024. A joint optimization of beam distribution and deployment for roadside LiDAR systems to maximize vehicle perception. IEEE Transactions on Intelligent Vehicles.

What we have on site

13 of 21

LiDAR (Top) View of the Intersection Testbed

13

16 Channel

128 Channel

64 Channel

14 of 21

Impact Analysis on Downstream Tasks

  • Object detection

  • Trajectory tracking and prediction

  • Scene Understanding and decision support for traffic management

14

[hitech 2024]

15 of 21

Task I. Object Detection (preliminary results)

15

Car

Van

Motorcycle

Trailer

Bus

Truck

16 of 21

Camera Under Off-Nominal Scenarios

16

Glare Scene

Night

Trucks mistakenly identified as cars

Due to night lighting issues, a non-existent truck was identified

17 of 21

Preliminary Results from On-site Experiments

17

(Average) Detection Accuracy for Various Traffic Participants

Distance to Intersection Center

Cameras

Mid - Resolution LiDAR

High -Resolution LiDAR

0-50m

90.8%

↑7.8%

↑8.1%

50-70m

76.1%

↑17.6%

↑20.9%

>70m

56.7%

↓40.7%

↓36.2%

  • Hi- and Med-resolution LiDARs outperform camera near the center region

18 of 21

Preliminary Results from On-site Experiments

18

(Average) Detection Accuracy for Various Traffic Participants

Distance to Intersection Center

Cameras

Mid - Resolution LiDAR

High -Resolution LiDAR

0-50m

90.8%

↑7.8%

↑8.1%

50-70m

76.1%

↑17.6%

↑20.9%

>70m

56.7%

↓40.7%

↓36.2%

  • Hi- and Med-resolution LiDARs outperform camera near the center region
  • Cameras maintain relatively higher accuracy at longer distances.

19 of 21

Comparison Between Hi- and Med-res LiDARs

19

The figure shows the detection accuracy of 128-C LiDAR and 64-C LiDAR for different types of objects in the range of 0-70m.

128-C

64-C

Motorcycle

20 of 21

Expected Outcomes

20

Open Data Platform for multi-resolution sensing

01

Facilitate AI Algorithms Development

03

Best Practices & Lessons Learned

01

02

Benchmark for Roadside Sensing

03

04

21 of 21

Q&A

  • Questions to dajiang.suo@asu.edu

21