The aim of this study was to test the performance of an automatic tracking software of features, FeatureTracker, developed for underwater motion analysis, and to compare it with another commercially available software, SIMI Motion System. Samples of 19 video recordings of different aquatic exercises (n=2340 frames) were manually tracked using the SIMI software in order to determine the markers center coordinates. Then they were automatically tracked using both the FeatureTracker and the SIMI software as follows: an operator stopped the automatic procedure in case the distance between the calculated marker and the reference one was higher than 4 pixels and then the action proceeded with a manual intervention in order to correct the cursor position. In all exercise modes, the manual intervention was required the 12% of the complete tracking procedure for the FeatureTracker and the 28% for the SIMI one, thus demonstrating the optimal automatic tracking performance of FeatureTracker. Therefore, the FeatureTracker software can be considered a valid tool for underwater motion analysis.
Performance analysis of an automatic tracking software in underwater exercises: Automatic tracking in underwater exercises / Magalhães F. A.;Sawacha Z.;Di Michele R. ;Cortesi M. ; Gatta G. ; Fantozzi S.. - ELETTRONICO. - (2012), pp. 54-57. (Intervento presentato al convegno XII International Symposium on 3D Analysis of Human Movement - Technology & Treatment tenutosi a Bologna nel 18-20 July 2012).
Performance analysis of an automatic tracking software in underwater exercises: Automatic tracking in underwater exercises
DI MICHELE, ROCCO;CORTESI, MATTEO;GATTA, GIORGIO;FANTOZZI, SILVIA
2012
Abstract
The aim of this study was to test the performance of an automatic tracking software of features, FeatureTracker, developed for underwater motion analysis, and to compare it with another commercially available software, SIMI Motion System. Samples of 19 video recordings of different aquatic exercises (n=2340 frames) were manually tracked using the SIMI software in order to determine the markers center coordinates. Then they were automatically tracked using both the FeatureTracker and the SIMI software as follows: an operator stopped the automatic procedure in case the distance between the calculated marker and the reference one was higher than 4 pixels and then the action proceeded with a manual intervention in order to correct the cursor position. In all exercise modes, the manual intervention was required the 12% of the complete tracking procedure for the FeatureTracker and the 28% for the SIMI one, thus demonstrating the optimal automatic tracking performance of FeatureTracker. Therefore, the FeatureTracker software can be considered a valid tool for underwater motion analysis.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
