Look Both Ways: Bidirectional Visual Sensing for Automatic Multi-Camera Registration

TL;DR

This paper presents a bidirectional visual sensing method using a mobile calibration robot with a fisheye camera and ArUco markers to automatically register large networks of fixed ceiling-mounted environment cameras over extensive areas.

Contribution

It introduces a novel bidirectional detection approach combining visual odometry and marker detection for large-scale multi-camera registration.

Findings

Validated with real-world experiments

Compared favorably against LiDAR-based methods

Effective for surveillance and robotic applications

Abstract

This work describes the automatic registration of a large network (approximately 40) of fixed, ceiling-mounted environment cameras spread over a large area (approximately 800 squared meters) using a mobile calibration robot equipped with a single upward-facing fisheye camera and a backlit ArUco marker for easy detection. The fisheye camera is used to do visual odometry (VO), and the ArUco marker facilitates easy detection of the calibration robot in the environment cameras. In addition, the fisheye camera is also able to detect the environment cameras. This two-way, bidirectional detection constrains the pose of the environment cameras to solve an optimization problem. Such an approach can be used to automatically register a large-scale multi-camera system used for surveillance, automated parking, or robotic applications. This VO based multi-camera registration method has been extensively validated using real-world experiments, and also compared against a similar approach which uses a LiDAR - an expensive, heavier and power hungry sensor.