Video based real-time positional tracker

TL;DR

This paper introduces a real-time video-based positional tracking system that uses multiple cameras and synthetic training data to achieve high accuracy and update rates, especially indoors or when GPS is unavailable.

Contribution

It presents a novel multi-camera video system trained on synthetic data for real-time indoor object positioning, surpassing GPS accuracy in occluded environments.

Findings

Higher update rate than GPS-based systems

Improved indoor positioning accuracy

Effective with occluded objects

Abstract

We propose a system that uses video as the input to track the position of objects relative to their surrounding environment in real-time. The neural network employed is trained on a 100% synthetic dataset coming from our own automated generator. The positional tracker relies on a range of 1 to n video cameras placed around an arena of choice. The system returns the positions of the tracked objects relative to the broader world by understanding the overlapping matrices formed by the cameras and therefore these can be extrapolated into real world coordinates. In most cases, we achieve a higher update rate and positioning precision than any of the existing GPS-based systems, in particular for indoor objects or those occluded from clear sky.