An All Deep System for Badminton Game Analysis

TL;DR

This paper presents a deep learning-based system for automatic badminton match analysis, focusing on improving shuttlecock detection accuracy to support event detection tasks, and achieving a high challenge score.

Contribution

The authors developed and refined deep learning models specifically for shuttlecock detection in badminton videos, addressing noise and data challenges to enhance precision.

Findings

Achieved a detection score of 0.78/1.0 in the challenge

Implemented modifications to the existing TrackNet model

Leveraged diverse data types to improve detection accuracy

Abstract

The CoachAI Badminton 2023 Track1 initiative aim to automatically detect events within badminton match videos. Detecting small objects, especially the shuttlecock, is of quite importance and demands high precision within the challenge. Such detection is crucial for tasks like hit count, hitting time, and hitting location. However, even after revising the well-regarded shuttlecock detecting model, TrackNet, our object detection models still fall short of the desired accuracy. To address this issue, we've implemented various deep learning methods to tackle the problems arising from noisy detectied data, leveraging diverse data types to improve precision. In this report, we detail the detection model modifications we've made and our approach to the 11 tasks. Notably, our system garnered a score of 0.78 out of 1.0 in the challenge. We have released our source code in Github https://github.com/jean50621/Badminton_Challenge