A fundamental purpose for movement is getting from point A to point B. This is typically the case in swimming and this activity is technically difficult. As a comparison of the three disciplines in a triathlon, it is considered the toughest to master. Humans are a land species and swimming requires synchronised actions in an environment that is somewhat foreign. Therefore assessing technical efficiency of swimming kinematics is of great importance. This efficiency includes coordination of arm; leg; and body movement parameters. Sports require assessment in actual environments and this includes swimming. Even on land, many events in an open environment are difficult to assess and extended periods of data capture are sometimes rare. In aquatic environments, assessment is considerably more difficult. Furthermore, open-water swimming is virtually impossible to monitor for objective performance analysis. The difficulty of assessing swimming arises due to the fluid medium (the water) in which it is performed and typically, video is used to capture swimming data. The problem with this technology is that the swimmer is usually performing at the air-water interface that can sometimes cause problems for effective filming due to parallax distortion and wash etc. Such issues do not affect micro sensors. Therefore using microtechnologies to measure swimming kinematics is a viable alternative to video measures. Micro sensor data capture dramatically reduces volume while providing detailed 3D analysis capabilities. In essence, this technology is a viable method for capturing human movement measures. Options of choosing single or multiple sensors for data capture offer dynamic assessment possibilities. Furthermore, multiple segment analysis is considerably quicker and quite cost effective when compared to a multiple video alternative. Using a small wearable device a swimmer can now train in their own pool and on their own but gather performance data like they were supported by coach and timekeeper and in an instrumented pool with video analysis. In general the measurement of sport specific performance characteristics is an important part of an athletes training and preparation for competition. Thus automated measurement, extraction and analysis of performance measures is desired and addressed in this paper. A tri-axial accelerometer based system was located on the lower back of swimmers to record acceleration profiles. The accelerometer system contained two ADXL202 bi-axial accelerometers positioned perpendicular to one another, the system could collect several hours worth of data. Simultaneous video and electronic touch pad timing was recorded for validation. Algorithms have been developed to derive lap times and stroke counts from the accelerometer data. Comparison against electronic touch pad timing against accelerometer lap times has produced results with a typical error of better than ±0.1 seconds. Video comparison of stroke count algorithm for freestyle also produced results with an average error of less than a single stroke. ![]() Next generation research is putting sensors on the hands and monitoring the propulsive forces as well to help improve technique more directly. Our ongoing resource developments make in-water research more viable where objective aquatic based assess ments at times are lacking. Australia prides it self as a dominant swimming nation and over time has often set the benchmark for international performance. Equally, the QSTC can say it too is setting benchmarks in the type and quality of testing carried out in swimming. Therefore playing an integral part in the continual performance improvement of the sport. This is reflected in the ICT Geelong, CSIRO-AIS Prize that was won in 201 |
Sports Technology >