Search

The velocities and distances covered by players during competition serve as a basis for planning fitness regimes according to the specific demand of the sport. The techniques used to calculate these movement parameters have ranged from human judgements to technological solutions such as GPS and computer vision. This paper evaluates the accuracy of a computerized motion tracking system (SAGIT/Squash) that uses computer vision methods on video captured via a fixed single camera located centrally above the court. Digital images were processed automatically with operator supervision so that any tracking errors could be rectified and manual tagging of all shots added. Four separate experiments were used to assess the error associated with tracking adult players' velocities and positions with respect to the court floor. Experiment 1 involved players standing still in different areas of the court. The tracking software was found to be more accurate when a player was stood in the centre of the court (1.33 m · min-1 error) than in the corners (2.61 m · min-1 error), predominately due to systematic errors (e.g. calibration). Experiment 2 was conducted in the same manner as Experiment 1 except that the players vigorously swung a racket around their body continuously. This resulted in 15 times the error found in Experiment 1 for the distance covered during 1 min. However, this is an unrealistic estimate of the true error when assessing matches, as during matches the racket is only swung approximately 35% of the time. Experiment 3 involved a player running at different speeds around a rectangular path on the court. The resultant trajectory, as captured by the software, was compared using different Gaussian smoothing equations of kernel widths 0.25 s, 0.5 s, and 1 s. The best solution (0.5 s) resulted in the most accurate trajectory, although the difference in distance calculated between the different equations was negligible. Experiment 4 used the 0.5-s smoothing equation to assess the tracking accuracy for a player running at a relatively steady speed in a more realistic circular trajectory. The trajectory of the pixel image was shown to have a smaller radius than the reference trajectory at increased speeds, due to the tendency of the player to lean over when negotiating a circular path. The error associated with the distance covered over 1 min was shown to range between 1.33 and 21 m depending on the nature and position of the player's movements. Values, typically somewhere in this range, are likely to be evident during typical use of this software. [ABSTRACT FROM AUTHOR]

The importance of dominating the T in squash is recognized by coaches and players but there has been little formal investigation of this aspect of tactical play. Consequently, the aim of this research was to analyse player occupancy of a T area, to establish whether there are differences between winners and losers of games at different playing standards. An automated player-tracking system, with operator supervision and intervention, captured players' movements during matches at the World Team Championships (n = 11), the Slovenian National Championships (n = 11), and a local tournament (n = 15). Frequency of occupying the T area at the moment opponents played their shot best discriminated playing standard. Winners spent a greater proportion of total playing time in the T area than losers (P < 0.001), except during closely contested games. The results suggest that time in the T area indicates dominance of rallies. Future studies need to consider both between-group (playing standard) and within-game (individual player standard) differences, as both were shown to influence the time players spent in the T area. [ABSTRACT FROM AUTHOR]