Document Detail


Measuring handball players trajectories using an automatically trained boosting algorithm.
MedLine Citation:
PMID:  21161798     Owner:  NLM     Status:  In-Data-Review    
Abstract/OtherAbstract:
The aim of the present paper is to propose and evaluate an automatically trained cascaded boosting detector algorithm based on morphological segmentation for tracking handball players. The proposed method was able to detect correctly 84% of players when applied to the second period of that same game used for training and 74% when applied to a different game. Furthermore, the analysis of the automatic training using boosting detector revealed general results such as the training time initially increased with the number of figures used, but as more figures were added, the training time decreased. Automatic morphological segmentation has shown to be a fast and efficient method for selecting image regions for the boosting detector and allowed an improvement in the automatic tracking of handball players.
Authors:
Ricardo M L Barros; Rafael P Menezes; Tiago G Russomanno; Milton S Misuta; Bruno C Brandao; Pascual J Figueroa; Neucimar J Leite; Siome K Goldenstein
Related Documents :
11183968 - Information requirements for clinical governance.
3745748 - A sequential procedure for implementing a computer-based information system.
12942248 - Easy and effective--web-based information systems designed and maintained by physicians...
22320338 - Comparison of indoor air quality management strategies between the school and district ...
11855778 - Complementary therapies courses for the 21st century.
4083118 - General and specific self-esteem in late adolescent students: race x gender x ses effects.
Publication Detail:
Type:  Journal Article     Date:  2010-12-01
Journal Detail:
Title:  Computer methods in biomechanics and biomedical engineering     Volume:  14     ISSN:  1476-8259     ISO Abbreviation:  Comput Methods Biomech Biomed Engin     Publication Date:  2011  
Date Detail:
Created Date:  2011-01-28     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9802899     Medline TA:  Comput Methods Biomech Biomed Engin     Country:  England    
Other Details:
Languages:  eng     Pagination:  53-63     Citation Subset:  IM    
Affiliation:
Department of Physical Education, University of Campinas, Campinas, Brazil.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Material parameter identification of arterial wall layers from homogenised stress-strain data.
Next Document:  Disinfection alternatives for contact surfaces and toys at child care centers.