Three-Dimensional Foot Position Estimation Based on Footprint Shadow Image Processing and Deep Learning for Smart Trampoline Fitness System.

In the wake of COVID-19, the digital fitness market combining health equipment and ICT technologies is experiencing unexpected high growth. A smart trampoline fitness system is a new representative home exercise equipment for muscle strengthening and rehabilitation exercises. Recognizing the motions of the user and evaluating user activity is critical for implementing its self-guided exercising system. This study aimed to estimate the three-dimensional positions of the user's foot using deep learning-based image processing algorithms for footprint shadow images acquired from the system. The proposed system comprises a jumping fitness trampoline; an upward-looking camera with a wide-angle and fish-eye lens; and an embedded board to process deep learning algorithms. Compared with our previous approach, which suffered from a geometric calibration process, a camera calibration method for highly distorted images, and algorithmic sensitivity to environmental changes such as illumination conditions, the proposed deep learning algorithm utilizes end-to-end learning without calibration. The network is configured with a modified Fast-RCNN based on ResNet-50, where the region proposal network is modified to process location regression different from box regression. To verify the effectiveness and accuracy of the proposed algorithm, a series of experiments are performed using a prototype system with a robotic manipulator to handle a foot mockup. The three root mean square errors corresponding to X, Y, and Z directions were revealed to be 8.32, 15.14, and 4.05 mm, respectively. Thus, the system can be utilized for motion recognition and performance evaluation of jumping exercises.

Return to competitive gymnastics training in the UK following the first COVID-19 national lockdown.

Following the outbreak of COVID-19 (coronavirus), the UK entered a national lockdown, and all sport was suspended. The study aimed to explore the process of returning to gymnastics training after several months away from the gym, with a particular interest towards training load and injury. Twenty-six, national programmed gymnasts from Men's artistic, Women's artistic and Trampoline gymnastics recorded training load and injury whilst returning to training. At the end of data collection, three coaches were interviewed to further explore the experiences and practices of returning to training. Home-based training during lockdown was seen as beneficial in maintaining a level of fitness. Coaches described a gradual increase in training to reduce the risk of injury, and this partly explains a non-significant association between training load and a substantial injury (p = 0.441). However, week-to-week changes in training load following periods of additional restrictions (additional lockdown, periods of isolation, or substantial restrictions) were not always gradual. There was a significant association between an injury in the preceding week (niggle or substantial injury to a different body part) and a substantial injury in the subsequent week (RR: 5.29, p = 0.011). Monitoring training was described to be a useful practice during the process of returning to training. Coaches believed that although the short-term development of their gymnasts was affected, the long-term development would not be impacted from COVID-19. It is anticipated that learnings from this study can be applied to future practices and situations, particularly when gymnasts are away from the gym for an extended period.

Trampolines injuries are bouncing back.

AIMS: This observational study examines the effect of the COVID-19 pandemic upon the paediatric trauma burden of a district general hospital. We aim to compare the nature and volume of the paediatric trauma during the first 2020 UK lockdown period with the same period in 2019. METHODS: Prospective data was collected from 23 March 2020 to 14 June 2020 and compared with retrospective data collected from 23 March 2019 to 14 June 2019. Patient demographics, mechanism of injury, nature of the injury, and details of any surgery were tabulated and statistically analyzed using the independent-samples t-test for normally distributed data and the Mann-Whitney-U test for non-parametric data. Additionally, patients were contacted by telephone to further explore the mechanism of injury where required, to gain some qualitative insight into the risk factors for injury. RESULTS: The 2020 lockdown resulted in 30% fewer paediatric trauma presentations (441 vs 306), but no significant change in the number of patients requiring surgery (47 vs 51; p = 0.686). Trampolining injuries increased in absolute numbers by 168% (p < 0.001), almost four times more common when considered as percentage of all injuries observed in 2020 vs 2019. There was a decrease in high energy trauma from road traffic accidents and falls from height (21.5% decrease, p < 0.001). Despite a shift towards more conservative treatment options, trampolining injuries continued to require surgery in similar proportions (19.4 vs 20%; p = 0.708). Qualitative investigation revealed that the most common risk factor for trampolining injury was concurrent usage, especially with an older child. CONCLUSION: COVID-19 lockdown has resulted in a decrease in paediatric orthopaedic presentations and high energy trauma. However, due to a marked increase in home trampolining injuries, and their unchanged requirement for surgery, there has been no change in the requirement for surgery during the lockdown period. As home exercise becomes more prevalent, a duty of public health falls upon clinicians to advise parents against trampoline usage. Cite this article: Bone Jt Open 2021;2(2):86-92.