Success case

Smart Transportation Utilizing 3D Scene Reconstruction to Identify Individual Distance and Number

Hardware: reComputer J202 carrier board for Jetson Nano/Xavier NX/TX2 NX module Use Case Provider: TECHRAIL Application: People Distance Identification &

Smart Transportation Utilizing 3D Scene Reconstruction to Identify Individual Distance and Number
Industry
Transportation & Logistics
Region
意大利米兰·车厢测试
Application
In-carriage headcount and distance
Results
Within 1% Identification accuracy error margin

Project background and needs

TECHRAIL used reComputer J202 with a Jetson module for passive-stereo 3D reconstruction in carriage tests in Milan, Italy, sending headcount and distance results to a central server.

Distance information

  • Traditional in-vehicle video monitoring has limits in accurately assessing distance between individuals.
  • Headcount alone isn't enough to describe spatial relationships inside the carriage.

Needs 3D reconstruction of the carriage interior.

Speed and resolution

  • Mechanically scanned LIDAR is limited by the actuator's rotation speed.
  • ToF cameras have limited spatial resolution and accuracy affected by ambient lighting.

Needs a vision solution balancing real-time performance and distance identification.

Solution and architecture

3D reconstruction

The reComputer J202 carrier board with a Jetson module processes passive-stereo data, combined with an object detection model to compute people's position, distance, and count.

Operational data

Results are stored locally and streamed to a central server in real time, letting control staff manage carriage data and station information panels.

Solution components

Discuss your application with our team

Tell us about your requirements and deployment environment.