Moving to VideoKifu: the last steps toward a fully automatic record-keeping of a Go game

TL;DR

This paper advances automatic Go game record-keeping by enabling real-time move sequence reconstruction from video streams, addressing new challenges and demonstrating promising preliminary results.

Contribution

It introduces methods for real-time Go move detection from video, extending previous image-based techniques to handle video-specific challenges.

Findings

Effective move detection in real-time video streams

Overcoming video-specific challenges for accurate reconstruction

Preliminary positive experimental results

Abstract

In a previous paper [ arXiv:1508.03269 ] we described the techniques we successfully employed for automatically reconstructing the whole move sequence of a Go game by means of a set of pictures. Now we describe how it is possible to reconstruct the move sequence by means of a video stream (which may be provided by an unattended webcam), possibly in real-time. Although the basic algorithms remain the same, we will discuss the new problems that arise when dealing with videos, with special care for the ones that could block a real-time analysis and require an improvement of our previous techniques or even a completely brand new approach. Eventually we present a number of preliminary but positive experimental results supporting the effectiveness of the software we are developing, built on the ideas here outlined.