Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis - - PowerPoint PPT Presentation

β–Ά
tac simur tactic based simulative visual analytics of
SMART_READER_LITE
LIVE PREVIEW

Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis - - PowerPoint PPT Presentation

Mar 26, 2024 47 likes β€’239 views

Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, and Yingcai Wu Speaker Wei Zheng Introduction Previous why tools are hard to use

slide-1
SLIDE 1

Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis

Speaker：Wei Zheng Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, and Yingcai Wu

slide-2
SLIDE 2

Introduction

2

why

  • Previous

tools are hard to use

  • Not effective

for tactic

what

  • A tool easy to

use and understand;

  • A model for

tactic;

how

  • A visualization

tool;

  • 2nd order

Markov chain model ;

slide-3
SLIDE 3

Table tennis match structure

[Fig 2. Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis. Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, Yingcai Wu. IEEE Trans. Visualization and Computer Graphics (Proc. Vis 2019), 26(1):407-417, 2019.]

match games rallies stroke tactic

slide-4
SLIDE 4
  • Collected manually
  • 9 kinds of stroke

placement

  • 13 kinds of stroke

technique

  • 4 kinds of stroke

position

Data

[Table 1. Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis. Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, Yingcai Wu. IEEE Trans. Visualization and Computer Graphics (Proc. Vis 2019), 26(1):407-417, 2019.]

slide-5
SLIDE 5

[Fig 1. Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis. Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, Yingcai Wu. IEEE Trans. Visualization and Computer Graphics (Proc. Vis 2019), 26(1):407-417, 2019.]

The overview of the Tac-Simur system

Data processing Model Visualization

  • Navigation: locate data
  • Exploration: support adjustments
  • Explanation: provides a

straightforward presentation

Expert requirements

slide-6
SLIDE 6

Model for simulation

[Fig 2. Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis. Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, Yingcai Wu. IEEE Trans. Visualization and Computer Graphics (Proc. Vis 2019), 26(1):407-417, 2019.]

𝐻𝑗 = {𝑆𝑗

1, 𝑆𝑗 2, …, 𝑆𝑗 π‘œ}

𝑆𝑗

π‘˜ = {𝑇𝑗,π‘˜ 1 , 𝑇𝑗,π‘˜ 2 , …, 𝑇𝑗,π‘˜ π‘œ , 𝑄𝑗 π‘˜}

Simulate the stroke sequence

slide-7
SLIDE 7

The First-order VS the Second-order Markov Chain Model

Original model new model.

[Fig 3. Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis. Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, Yingcai Wu. IEEE Trans. Visualization and Computer Graphics (Proc. Vis 2019), 26(1):407-417, 2019.]

  • Inadequate Tactic Modeling
  • considering 2 previous strokes in

2nd order Markov chain model

  • Insufficient Stroke Characterization
  • expanded the number of attributes

used in stroke characterization to three

slide-8
SLIDE 8

The First-order VS the Second-order Markov Chain Model

Original model New model

[Fig 3. Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis. Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, Yingcai Wu. IEEE Trans. Visualization and Computer Graphics (Proc. Vis 2019), 26(1):407-417, 2019.]

Β· + Β·

π‘Šπ‘™ = Ξ»1 Β· Vπ‘™βˆ’1 T1 Ξ»2 Β· Vπ‘™βˆ’2 T2

  • The different phases in a rally are simulated

by different Markov processes.

slide-9
SLIDE 9

[Fig 4. Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis. Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, Yingcai Wu. IEEE Trans. Visualization and Computer Graphics (Proc. Vis 2019), 26(1):407-417, 2019.]

Model evaluation

  • Higher recall rates
  • Higher precision
slide-10
SLIDE 10

[Fig 5. Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis. Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, Yingcai Wu. IEEE Trans. Visualization and Computer Graphics (Proc. Vis 2019), 26(1):407-417, 2019.]

System design

Main view

slide-11
SLIDE 11

[Fig 6. Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis. Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, Yingcai Wu. IEEE Trans. Visualization and Computer Graphics (Proc. Vis 2019), 26(1):407-417, 2019.]

System design

Explanation view

slide-12
SLIDE 12

Let’s watch a video showing system in action

12

https://www.youtube.com/watch?v=_I6cne3Wd4U

slide-13
SLIDE 13

System evaluation

[Fig 7. Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis. Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, Yingcai Wu. IEEE Trans. Visualization and Computer Graphics (Proc. Vis 2019), 26(1):407-417, 2019.]

Step1: find pattern in tech view

slide-14
SLIDE 14

System evaluation

[Fig 7. Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis. Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, Yingcai Wu. IEEE Trans. Visualization and Computer Graphics (Proc. Vis 2019), 26(1):407-417, 2019.]

Step2: Generate optimum strategy

slide-15
SLIDE 15

System evaluation

[Fig 7. Tac-Simur: Tactic-based Simulative Visual Analytics of Table Tennis. Jiachen Wang, Kejian Zhao, Dazhen Deng, Anqi Cao, Xiao Xie, Zheng Zhou, Hui Zhang, Yingcai Wu. IEEE Trans. Visualization and Computer Graphics (Proc. Vis 2019), 26(1):407-417, 2019.]

Step3: Check explanation

slide-16
SLIDE 16

Analysis summary

  • What: data

Table of strokes

  • How: encode

Color, spatial, node-link Bar, glyphs

  • How: change

animation

slide-17
SLIDE 17

Critique

Strengths:

  • Provide a suitable model for the simulative analysis of

table tennis;

  • Design a user-friendly visualization tool.
slide-18
SLIDE 18

Critique

Weaknesses:

  • Fail to give proof why Markov chain is better than deep

learning;

  • Three features for strokes are not enough, should have

the force of the stroke, rotation speed of the ball

  • The way to encode stroke position is not intuitive

forehand backhand Backhand turn Pivot

slide-19
SLIDE 19

Thanks!