Do-It-Yourself Single Camera 3D Pointer Input Device

TL;DR

This paper introduces a cost-effective single-camera system for 3D pointer tracking that uses a patterned elongated object, enabling accurate 3D input for human-computer interaction without complex multi-camera setups.

Contribution

A novel algorithm for 3D reconstruction from a single camera using a patterned pointer, reducing system complexity and cost compared to existing multi-camera solutions.

Findings

Robust 3D pointer tracking with occlusion handling

Accurate 3D localization demonstrated with known geometric objects

System requires minimal calibration data

Abstract

We present a new algorithm for single camera 3D reconstruction, or 3D input for human-computer interfaces, based on precise tracking of an elongated object, such as a pen, having a pattern of colored bands. To configure the system, the user provides no more than one labelled image of a handmade pointer, measurements of its colored bands, and the camera's pinhole projection matrix. Other systems are of much higher cost and complexity, requiring combinations of multiple cameras, stereocameras, and pointers with sensors and lights. Instead of relying on information from multiple devices, we examine our single view more closely, integrating geometric and appearance constraints to robustly track the pointer in the presence of occlusion and distractor objects. By probing objects of known geometry with the pointer, we demonstrate acceptable accuracy of 3D localization.