| Autor: |
Barcelos EZ; Department of Electrical Engineering, Federal University of Triangulo Mineiro, Av. Dr. Randolfo Borges Jr. 1250, Univerdecidade, CEP 38064.200, Uberaba, MG, Brazil. emilio.barcelos@icte.uftm.edu.br., Caminhas WM; Department of Electronics Engineering, Graduate Program in Electrical Engineering, Federal University of Minas Gerais, Av. Antonio Carlos 6627, Pampulha, CEP 31270.901, Belo Horizonte, MG, Brazil. caminhas@cpdee.ufmg.br., Ribeiro E; Department of Computer Sciences, Florida Institute of Technology, 150 West University Blvd, Melbourne, FL 32901, USA. eribeiro@cs.fit.edu., Pimenta EM; Medical and Physiology Department, Cruzeiro Esporte Clube, R. Adolfo Lippi Fonseca, 251, Céu Azul, CEP 31545.260, Belo Horizonte, MG, Brazil. empimenta@uol.com.br., Palhares RM; Department of Electronics Engineering, Graduate Program in Electrical Engineering, Federal University of Minas Gerais, Av. Antonio Carlos 6627, Pampulha, CEP 31270.901, Belo Horizonte, MG, Brazil. palhares@cpdee.ufmg.br. |
| Abstrakt: |
In this paper, a method that combines image analysis techniques, such as segmentation and registration, is proposed for an advanced and progressive evaluation of thermograms. The method is applied for the prevention of muscle injury in high-performance athletes, in collaboration with a Brazilian professional soccer club. The goal is to produce information on spatio-temporal variations of thermograms favoring the investigation of the athletes' conditions along the competition. The proposed method improves on current practice by providing a means for automatically detecting adaptive body-shaped regions of interest, instead of the manual selection of simple shapes. Specifically, our approach combines the optimization features in Otsu's method with a correction factor and post-processing techniques, enhancing thermal-image segmentation when compared to other methods. Additional contributions resulting from the combination of the segmentation and registration steps of our approach are the progressive analyses of thermograms in a unique spatial coordinate system and the accurate extraction of measurements and isotherms. |
