Sports Analytics Giuseppe Prencipe Dipartimento di Informatica - - PowerPoint PPT Presentation

▶
sports analytics
SMART_READER_LITE
LIVE PREVIEW

Sports Analytics Giuseppe Prencipe Dipartimento di Informatica - - PowerPoint PPT Presentation

Oct 23, 2022 220 likes •396 views

Sports Analytics Giuseppe Prencipe Dipartimento di Informatica Universit di Pisa #1 Collect data #2 Analyse them 5BN/year market #1 #3 Collect data Automatically #2 Analyse them 5BN/year market MAIN SPORT-TECH CLUSTERS Athletic

slide-1
SLIDE 1

Sports Analytics

Giuseppe Prencipe

Dipartimento di Informatica Università di Pisa

slide-2
SLIDE 2

Analyse them

#2

Collect data

#1

5BN/year market

slide-3
SLIDE 3

Analyse them

#2

Automatically

#3

Collect data

#1

5BN/year market

slide-4
SLIDE 4

MAIN SPORT-TECH CLUSTERS

Athletic Performance Smart Arena Immersive Media Fan Experience Club Management E-Sports

slide-5
SLIDE 5

MAIN SPORT-TECH CLUSTERS

Athletic Performance Smart Arena Immersive Media Fan Experience Club Management E-Sports

slide-6
SLIDE 6

At our Department

PlayeRank

slide-7
SLIDE 7

m i d f i e l d e r r i g h t w i n g l e f t w i n g f

  • r

w a r d l e f t f i e l d e r l e f t b a c k r i g h t f i e l d e r r i g h t b a c k

PlayeRank data-driven performance evaluation

slide-8
SLIDE 8

Univ of Connecticut USA FC Barcelona
 Spain

Injury Forecasting

Collaborations

Ferencvárosi TC
 Hungary Philadelphia 76ers
 USA

Done: AI-based Injury Forecaster (IF) for soccer players Ongoing: Explainable AI tool to help staff interpret predictions the IF Future work: Generator of injury-free training plans, based on Adversarial Learning and Generative Adversarial Networks (GANs)

PlayeRank

slide-9
SLIDE 9

UEFA
 Europe

Tactical Analysis

Collaborations Done: AI-based evaluators for teams and players Ongoing: Explainable AI tools for forecasting career evolution of players and performance of teams Future work:

  • Match simulators based on GANs
  • Optimal team formation
  • Automatic commentator

Fraunhofer
 Bonn, Germany Northeastern Univ.
 Boston, USA Queen Mary Univ.
 London, UK FIGC
 Italy

PlayeRank

slide-10
SLIDE 10
slide-11
SLIDE 11

11

slide-12
SLIDE 12

Live AI data interpretation Video analysis Live Stroke analysis & Heatmap Social network

slide-13
SLIDE 13

Problem 1: position tracking Problem 2: tracking arm’s movements with smartwatch Problem 3: coaching

Video processing, with object detection + projection on the court, using keypoints to calibrate Classification with supervised learning of the gesture (data from accelerometer and gyroscope) Profile of the player and adaptive expert system for real-time strategic support

slide-14
SLIDE 14

Ongoing & Future work:

  • Effective position tracking for double
  • Automatic calibration
  • Pose estimation and ML to track arm’s movements through video
  • Energy issues
  • Tackle other sports
slide-15
SLIDE 15

JNE 3, 2016 17:47

b FEDEICO COINI IE 6871

Eer tennis plaers pet peee is nderperforming dring a game, for no apparent reason, has this eer happened to

  • ?

E

He Tei Ne Ohe Ne

' ,

  • - ? I ! '

ENNI COMMANDER: , . ENNI COMMANDER A , . A I , , . F , ENNI COMMANDER , ' . O, , ENNI

TODAY'S MOST POPULAR

E F C IF R N N D' R F: ' . L , N, D' R N , L M NE NE MLIMEDIA MLIMEDIA ECHNIQE ECHNIQE RANKING RANKING LIE LIE

K K K K N D N D

Peed b: Wd(D) 1.6 Peed b: Wd(D) 1.6

Seac e Login Register

  • ,

Chidi

JNE 3, 2016 17:47

b FEDEICO COINI IE 6871

Eer tennis plaers pet peee is nderperforming dring a game, for no apparent reason, has this eer happened to

  • ?

E

He Tei Ne Ohe Ne

' ,

  • - ? I ! '

ENNI COMMANDER: , . ENNI COMMANDER A , . A I , , . F , ENNI COMMANDER , ' . O, , ENNI

TODAY'S MOST POPULAR

E F C IF R N N D' R F: ' . L , N, D' R N , L M NE NE MLIMEDIA MLIMEDIA ECHNIQE ECHNIQE RANKING RANKING LIE LIE

K K K K N D N D

Peed b: Wd(D) 1.6 Peed b: Wd(D) 1.6

Seac e Login Register

  • ,

Chidi

Colpi nello smartwatch l’app prototipo è italiana

Dall’Università di Pisa un nuovo passo avanti nel tennis connesso Pag.22

Anno XII - n.22 - 8 giugno 2016

Stampa Stampa senza immagine Chiudi EAABLE

Tenni, ar no marach ad allenari per il colpo perfeo

L, , :

Peppe Aqao N . C . C . E . M .

N EAM INSOLIO

I , , , : , . I, , G P, T C, T A. C C A M. P I P, . I , A, ( ) .

COLPI DA MAESRO CON GLI ALGORIMI

I , , : C ?. A , , . T . N , , , , achie leaig,

Stampa Stampa senza immagine Chiudi EAABLE

Tenni, ar no marach ad allenari per il colpo perfeo

L, , :

Peppe Aqao N . C . C . E . M .

N EAM INSOLIO

I , , , : , . I, , G P, T C, T A. C C A M. P I P, . I , A, ( ) .

COLPI DA MAESRO CON GLI ALGORIMI

I , , : C ?. A , , . T . N , , , , achie leaig,

slide-16
SLIDE 16

Giuseppe Prencipe

giuseppe.prencipe@unipi.it

contacts

Paolo Ferragina

paolo.ferragina@unipi.it

Luca Pappalardo

luca.pappalardo@unipi.it

Paolo Cintia

paolo.cintia@isti.cnr.it References:

  • PlayeRank: data-driven performance evaluation and player ranking in soccer via a machine learning approach.
  • L. Pappalardo et al. ACM TIST, 2019
  • Explainable Injury Forecasting in Soccer via Multivariate Time Series and Convolutional Neural Networks.
  • L. Pappalardo et al. BARÇA Sports Analytics Summit, 2019
  • Who is going to get hurt? Predicting injuries in professional soccer. A. Rossi et al. In Proceedings of MLSA’17