Estimation of player trajectories from context in football games using autoencoders
ChyronHego tracks a large number of football games. Occasionally there are errors in the tracked positions of the ball or the players. This thesis aims to investigate to what extent vanilla autoencoders, variational autoencoders and conditional variational autoencoders can recognise patterns in the...
Main Author: | Deprette, Manon |
---|---|
Format: | Others |
Language: | English |
Published: |
KTH, Skolan för elektroteknik och datavetenskap (EECS)
2020
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-280698 |
Similar Items
-
Time Series Anomaly Detection and Uncertainty Estimation using LSTM Autoencoders
by: Berenji Ardestani, Sarah
Published: (2020) -
Anomaly Detection in Credit Card Transactions using Autoencoders
by: Nordling, Carl
Published: (2020) -
Anomaly Detection in Networks using Autoencoder and Unsupervised Learning Methods
by: Azmoudeh Fard, Simon
Published: (2021) -
Training Autoencoders for feature extraction of EEG signals for motor imagery
by: Wahl, Casper
Published: (2021) -
Real-time Head Pose Estimation inLow-resolution Football Footage UsingRandom Forests
by: DÜBBEL, ANDRÉ
Published: (2013)