Human performance can be enhanced through considered deployment of modern technologies in a wide range of domains and environments. CAMERA researchers have recently had four papers published in the field; two accepted at conferences for the International Society of Biomechanics in Sports 2020 and CVPR Sports 2020, and two full published papers.

CAMERA Co-Investigator, Dr Steffi Colyer said “It’s fantastic to see such great progress in our research within the Human Performance Enhancement theme. Each of these studies have required a huge team effort, often requiring the fusion of different disciplines and expertise (e.g. computer vision, machine learning and sports biomechanics) in order to address complex problems. We thank our partners (the British Bobsleigh and Skeleton Association) and our international collaborators for their continued support.”

Using Computer Vision and Deep Learning Methods to Capture Skeleton Push Start Performance. Needham, L., Evans, M., Cosker, D. & Colyer, S. International Society of Biomechanics in Sports 2020

Abstract: This study aimed to employ computer vision and deep learning methods in order to capture skeleton push start kinematics. Push start data were captured concurrently by a markerbased motion capture system and a custom markerless system. Very good levels of agreement were found between systems, particularly for spatial based variables (step length error 0.001 ± 0.012 m) while errors for temporal variables (ground contact time and flight time) were within 1.5 frames of the criterion measures. The computer vision based methods tested in this research provide a viable alternative to marker-based motion capture systems. Furthermore they can be deployed into challenging, real world environments to non-invasively capture data where traditional approaches would fail.

Paper

A non-invasive vision based approach to velocity measurement of Skeleton training. Evans, M., Needham, L., Colyer, S., Cosker, D. CVPR Sports 2020

Abstract: Skeleton is a winter sport where performance is greatly affected by the velocity an athlete can achieve during their start up to the point where they load themselves onto their sled. As such, it is of interest to athletes and coaching staff to be able to monitor the performance of their athletes and how they respond to different training schedules and techniques. This paper proposes a non-invasive vision based method for measuring the velocity of a skeleton athlete and their sled during the push start. Mean differences in estimated velocity between ground truth data and our proposed system were -0.005 ( 0.186) m.s-1 for the athlete mass centre and -0.017 ( 0.133) m.s-1 for the sled. The results compare favourably to techniques previously presented in the biomechanics and sport science literature.

Paper

Examples of sled corner detections. Circles are coloured based on the corner label, with confidence indicated by the brightness of the circle interior. Many of the detections are of the quality of the top right and middle left examples, but a number of different failure cases have been observed as evidenced here.

Full papers

Differences in ground reaction waveforms between elite senior and junior academy sprinters during the block phase and first two steps. Graham-Smith, P., Colyer, S. & Salo, A. March 2020. International Journal of Sports Science & Coaching.

Abstract: The block start and initial steps following block exit are fundamental aspects of sprinting and their development is key to junior athletes’ progression. This study assessed the difference in force production between elite senior (including two sub-10 s 100-m sprinters) and junior academy sprinters during the block phase and the first two steps of a sprint. Thirty-seven male sprinters (17 senior, 20 junior) performed a series of maximal-effort 20-40 m acceleration from blocks on an indoor track, with the ground reaction forces produced during the block phase and first two steps measured using force platforms. Senior athletes produced better block phase performances (average horizontal external power; 15.52±1.48 W/kg, mean±SD) compared with the juniors (12.37±2.21 W/kg; effect size±90% CI = 1.28±0.38). However, force production during the initial two steps was comparable across groups. Specifically, senior athletes exhibited higher relative force production and ratio of forces during the early (~15- 35%) block phase and higher anteroposterior forces during the transition from bilateral to unilateral pushing (58-62% of the block phase). Front foot force production was also found to differentiate senior and junior groups at rear block exit (~55% of the block phase). This may be a required response to the greater centre of mass displacement in order to prevent overrotation in the senior athletes during the front block pushing phase. Collectively, these results indicate that the progression of junior athletes is non-uniform across the block phase and subsequent two contacts, which should be considered when attempting to progress junior athletes towards senior ranks.

Paper

The effect of biological maturity status on ground reaction force production during sprinting. Colyer, S., Nagahara, R., Takai, Y. & Salo, A. April 2020. Scandanavian Journal of Medicine & Science in Sports.

Abstract: Sprint ability develops non-linearly across childhood and adolescence. However, the underpinning ground-reaction-force (GRF) production is not fully understood. This study aimed to uncover the kinetic factors that explain these maturation-related sprint performance differences in Japanese boys and girls. A total of 153 untrained schoolchildren (80 boys, 73 girls) performed two 50-m maximal-effort sprints over a 52-force-platform system embedded in an indoor track. Maturity offset (years from peak height velocity; PHV) was estimated using anthropometric data and used to categorise the children into six year-long maturation groups (from group 1 [5.5-4.5 years before PHV] to group 6 [0.5 years before to 0.5 years after PHV). Maximum and mean step-averaged velocities across 26 steps were compared across consecutive maturation groups, with further GRF analysis (means and waveforms [statistical parametric mapping]) performed when velocity differences were observed. For boys, higher maximum velocities (effect size±90% CI = 1.63±0.69) were observed in maturation group 2 (4.5-3.5 years before PHV) compared to group 1 (5.5-4.5 years before PHV), primarily attributable to higher anteroposterior GRFs across shorter ground contacts. Maximum velocities increased from maturation group 4 (2.5-1.5 years before PHV) to 5 (1.5-0.5 years before PHV) in the girls (effect size±90% CI = 1.00±0.78), due to longer ground contacts rather than higher GRFs per se. Waveform analyses revealed more effective reversal of braking forces and higher propulsive forces (e.g. 14-77% of stance 4), particularly for comparisons involving boys, which suggested potentially enhanced stretch-shortening ability. Youth-sport practitioners should consider these maturation-specific alterations when evaluating young athletes’ sprint abilities.

Paper

You can explore our research in this area at www.camera.ac.uk/themes/human-performance-enhancement