# calibDB: enabling web based computer vision through on-the-fly camera calibration

## TL;DR

CalibDB is a web-based service that aggregates and enables on-the-fly calibration of cameras, facilitating the deployment of computer vision applications on the web even for users without calibration data.

## Contribution

It introduces a novel, user-friendly calibration framework and a web service that allows real-time calibration of new cameras, expanding web-based computer vision capabilities.

## Key findings

- Calibration can be performed in about 2 minutes.
- The service enables deployment of vision algorithms on uncalibrated cameras.
- It democratizes access to calibration data for web applications.

## Abstract

For many computer vision applications, the availability of camera calibration data is crucial as overall quality heavily depends on it. While calibration data is available on some devices through Augmented Reality (AR) frameworks like ARCore and ARKit, for most cameras this information is not available. Therefore, we propose a web based calibration service that not only aggregates calibration data, but also allows calibrating new cameras on-the-fly. We build upon a novel camera calibration framework that enables even novice users to perform a precise camera calibration in about 2 minutes. This allows general deployment of computer vision algorithms on the web, which was previously not possible due to lack of calibration data.