Reviving Direct Observation Methods for Physical Activity Behavior

作     者：Pedro Miguel Ribeiro da Silva Sérgio Hélder da Silva Soares Soares Jorge Augusto Pinto Silva Mota Paula Maria Marques Moura Gomes Viana Pedro Miguel Machado Soares Carvalho 

作者机构：CIAFELFaculty of SportsUniversity of PortoPorto4200-450Portugal School of EngineeringPolytechnic of PortoPorto4200-072Portugal INESC TECPorto4200-465Portugal 

出 版 物：《Journal of Sports Science》 (运动科学（英文版）)

年 卷 期：2021年第9卷第1期

页      面：9-16页

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was funded by the Portuguese Foundation for Science and Technology(FCT),grant SFRH/BPD/71332/2010,Pest-OE/SAU/UI0617/2011 and UIDB/50014/2020 The work was also developed in the context of Project QREN 33910 ARENA,a R&D project funded by ERDF through ON2 as part of the NSRF,and managed by IAPMEI-Agência para a Competitividade e Inovação,I.P 

主　　题：Measuring physical behavior systematic observation movement intensity video 

摘      要：Purpose:Current Direct Observation(DO)methods are burdensome to the observer and relevant limitations can be identified on the outcome *** study aims to characterize DO from the observers’point of view and to analyze the feasibility and usefulness of visual information in the form of ***:data collection was done with ten adult males,observed while performing different physical activities in an indoor *** were video recorded by two *** observers performed systematic observation,using SOPLAY,with different sampling *** observer’s agreement and with reference data was analyzed by Cohen’s Kappa ***:SOPLAY highest agreement between observers was 0.611 on vigorous category and walking category had the lowest *** doubles the time needed to annotate the video with pauses,but half of player’s behavior is ***(s):using video to support DO permits to collect more accurate data and a more detailed behavior categorization is *** in computer vision are expected to reduce the human efforts in DO methods.