A Two-point Method for PTZ Camera Calibration in Sports

TL;DR

This paper introduces a novel two-point calibration method for PTZ cameras in sports, requiring minimal correspondences and prior knowledge, and combines it with a fast random forest approach for efficient angle prediction in soccer videos.

Contribution

The paper presents a new two-point calibration technique for PTZ cameras and a fast random forest method for angle prediction, improving efficiency and accuracy over existing methods.

Findings

Achieves superior calibration accuracy compared to state-of-the-art methods.

Demonstrates effectiveness on synthetic and real soccer datasets.

Reduces calibration time with a fast random forest approach.

Abstract

Calibrating narrow field of view soccer cameras is challenging because there are very few field markings in the image. Unlike previous solutions, we propose a two-point method, which requires only two point correspondences given the prior knowledge of base location and orientation of a pan-tilt-zoom (PTZ) camera. We deploy this new calibration method to annotate pan-tilt-zoom data from soccer videos. The collected data are used as references for new images. We also propose a fast random forest method to predict pan-tilt angles without image-to-image feature matching, leading to an efficient calibration method for new images. We demonstrate our system on synthetic data and two real soccer datasets. Our two-point approach achieves superior performance over the state-of-the-art method.