ESC: Evolutionary Stitched Camera Calibration in the Wild

TL;DR

This paper presents ESC, an end-to-end evolutionary algorithm for accurate multi-camera calibration on sports fields, improving virtual stitched views and outperforming existing methods in real-world scenarios.

Contribution

The paper introduces ESC, a novel evolutionary optimization-based calibration method that addresses real-world challenges and improves accuracy for multi-camera sports field setups.

Findings

ESC outperforms state-of-the-art calibration methods

High visual fidelity in stitched multi-camera views

Effective calibration across diverse sports field environments

Abstract

This work introduces a novel end-to-end approach for estimating extrinsic parameters of cameras in multi-camera setups on real-life sports fields. We identify the source of significant calibration errors in multi-camera environments and address the limitations of existing calibration methods, particularly the disparity between theoretical models and actual sports field characteristics. We propose the Evolutionary Stitched Camera calibration (ESC) algorithm to bridge this gap. It consists of image segmentation followed by evolutionary optimization of a novel loss function, providing a unified and accurate multi-camera calibration solution with high visual fidelity. The outcome allows the creation of virtual stitched views from multiple video sources, being as important for practical applications as numerical accuracy. We demonstrate the superior performance of our approach compared to state-of-the-art methods across diverse real-life football fields with varying physical characteristics.