HomeRobotics & KinematicsMulti-Camera Line-Call Triangulation

Multi-Camera Line-Call Triangulation (2D)

Interactive 2D top-down simulator of automated sports line-calling: drag cameras around the court, fire a ball across the line, and watch a real least-squares bearing-only triangulation solve for the bounce point — with an analytic uncertainty ellipse that stretches when camera geometry is poor.

Robotics & Kinematics2DAdvanced60 FPS📱 Mobile-adapted⇄ 3D version
2d-robotics-topic-102 ↗ Open standalone

This is the flat, top-down mechanics behind automated sports line-calling: a camera never reports a position, only a bearing — a ray from a known point. Drag the camera icons anywhere around the court, set how noisy each bearing is, then fire the ball across the line. The engine genuinely solves a least-squares intersection of the noisy rays for the bounce point, draws the real uncertainty ellipse implied by the current camera geometry, and runs 200-trial Monte-Carlo batches so you can verify with real numbers — not just visually — that a poor camera spread produces a bigger ellipse and more missed line calls than a good one.

⚙ Under the hood

Simulate automated sports line-calling: multiple cameras triangulate a ball's bounce point by solving a least-squares ray-intersection system, then compare the system's IN/OUT call against ground truth as camera count and pixel noise change.

roboticscomputer visiontriangulationsports techsensor fusionleast squares

2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)