Non-invasive, Spatio-temporal Gait Analysis for Sprint Running Using a Single Camera

Abstract

Sprint running velocity is the product of step length and step rate. A tool to measure these key metrics would aid sprint training. Athletes require fast and non-invasive analysis tools, to allow them to focus on performance. A non-invasive, single camera gait analysis system (Gait Analyser) was developed and installed at the Sheffield Hallam University City Athletics Stadium (SHUCAS). The Gait Analyser filmed athletes sprinting in lanes 1, 5 and 8 wearing different coloured shoes in varied lighting conditions (e.g. sunlight or overcast). The Gait Analyser automatically identified the position and time of athlete's foot contacts, allowing the calculation of step length, step time and step velocity. Output data were compared to corresponding, manually identified measurements. For optimised setups, 100% of foot contacts were identified. Resultant direction root-mean square error (RMSE) for foot contact position and time was 108.9 mm and 0.03 s respectively. RMSE for step length, step time and step velocity was 4.9 mm, 0.00 s and 0.07 m·s -1 respectively. The Gait Analyser measured spatio-temporal gait parameters of sprint running in situ without applying markers or sensors to the athlete or the running track: results were available 2-3 s after capture.

Detection of Ground Contact Times with Inertial Sensors in Elite 100-m Sprints under Competitive Field Conditions

“…Temporal parameters, in which tiny deviations can play a decisive role, and can only be captured with technological aid. Established methods like video footage, timing gates, contact mats, motion capturing, or force plates are used to determine exact temporal sprint parameters [8][9][10]. The feedback obtained by these methods can improve the quality of the running technique.…”

Automatic high fidelity foot contact location and timing for elite sprinting

“…Intuitively quite simple, a lot of processing is required to handle false detections which can more easily be removed with multiple viewpoints, and using a single camera, although convenient, will limit positional accuracy, especially if a large area is to be covered. The system of Dunn [13] is multicamera and may be the most comparable to the Obsmos system, but technical details are limited. They do provide a benchmark against which to measure performance however, reporting −4.9 ± 177.7 mm and 0.0 ± 0.03 s (Bland and Altman 95% limits of agreement) against manual digitisation.…”

“…Step length results can be directly compared with the video system of Dunn [13] which was reported to have −4.9 ± 177.7 mm (Bland and Altman 95% limits of agreement). In comparison, the Obsmos system is more accurate (has less bias) and more precise, at 0.52 ± 12.58mm for step length, and Fused OpenPose is also better at 1.68 ± 48.33mm.…”

Development of Smart Inner City Recreational Facilities to Encourage Active Living

“…Camera calibration parameters are retrieved from a database, allowing the calculation of real-world, spatio-temporal gait parameters. It has been reported that the system identified 100% of foot contacts (optimised setup) during sprint running; root-mean-square error was 108.9 mm and 0.03 s for foot contact position and time respectively [16]. Further, numeric and video results were provided to athletes within 2-3 s of capture.…”