Overview
What this challenge is about.
You receive 6 hours of synced LiDAR + 4-camera ring data from yard operations, with 3D bounding-box labels for pedestrians, forklifts, and containers. Build a late-fusion module that takes a LiDAR 3D detector's output (provided baseline) and a 2D image detector's output (also provided) and produces a fused track list. Measure improvement in pedestrian recall at the same precision against the LiDAR-only baseline, separately for sunny and overcast slices. Deliver the fusion module, an evaluation report, and a one-page integration spec the perception lead can hand to a production engineer.
The Brief
What you'll do, and what you'll demonstrate.
Lift pedestrian recall under bright-sun conditions via a late-fusion module without hurting precision elsewhere.
Earning criteria — what you'll demonstrate
- Apply late-fusion strategies to combine LiDAR and camera detections
- Evaluate detection improvements at fixed precision
- Slice metrics by environmental condition to expose real-world gains
- Translate a prototype into a production-ready integration spec
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Computer Vision Engineer
LiDAR-camera fusion with sliced evaluation under real environmental conditions is core CV-engineer work at any autonomous-vehicle or yard-automation company.
This challenge sharpens
- sensor-fusion
- lidar-perception
- object-detection
Machine Learning Engineer
Shipping a prototype with an integration spec for a production engineer mirrors how MLEs hand off perception components in robotics teams.
This challenge sharpens
- python
- evaluation
- 3d-perception
Applied AI Scientist
Designing and ablating a fusion strategy against a fixed-precision target is the applied-AI scientist's bread and butter on perception teams.
This challenge sharpens
- sensor-fusion
- evaluation
- 3d-perception