Back to articles
Volume: 29 | Article ID: art00004
Goal!! Event detection in sports video
  DOI :  10.2352/ISSN.2470-1173.2017.16.CVAS-344  Published OnlineJanuary 2017

Understanding complex events from unstructured video, like scoring a goal in a football game, is an extremely challenging task due to the dynamics, complexity and variation of video sequences. In this work, we attack this problem exploiting the capabilities of the recently developed framework of deep learning. We consider independently encoding spatial and temporal information via convolutional neural networks and fusion of features via regularized Autoencoders. To demonstrate the capacities of the proposed scheme, a new dataset is compiled, compose of goal and no-goal sequences. Experimental results demonstrate that extremely high classification accuracy can be achieved, from a dramatically limited number of examples, by leveraging pre-trained models with fine-tuned fusion of spatio-temporal features.

Subject Areas :
Views 190
Downloads 24
 articleview.views 190
 articleview.downloads 24
  Cite this article 

Grigorios Tsagkatakis, Mustafa Jaber, Panagiotis Tsakalides, "Goal!! Event detection in sports videoin Proc. IS&T Int’l. Symp. on Electronic Imaging: Computer Vision Applications in Sports,  2017,  pp 15 - 20,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2017
Electronic Imaging
Society for Imaging Science and Technology