Accurate 3D human pose estimation from single images is possible with sophisticated deep-net architectures that have been trained on very large datasets. However, this still leaves open the problem of capturing motions for which no such database exists. Manual annotation is tedious, slow, and error-prone. In this paper, we propose to replace most of the annotations by the use of multiple views, at training time only. Specifically, we train the system to predict the same pose in all views. Such a consistency constraint is necessary but not sufficient to predict accurate poses. We therefore complement it with a supervised loss aiming to predict the correct pose in a small set of labeled images, and with a regularization term that penalizes drift from initial predictions. Furthermore, we propose a method to estimate camera pose jointly with human pose, which lets us utilize multiview footage where calibration is difficult, e.g., for pan-tilt or moving handheld cameras. We demonstrate the effectiveness of our approach on established benchmarks, as well as on a new Ski dataset with rotating cameras and expert ski motion, for which annotations are truly hard to obtain.

Ultrasound (US) imaging has been widely used in both research and clinical settings to evaluate the morphological and mechanical properties of muscle and tendon. In elite sports scenarios, a regular assessment of such properties has great potential, namely for testing the response to training, detecting athletes at higher risks of injury, screening athletes for structural abnormalities related to current or future musculoskeletal complaints, and monitoring their return to sport after a musculoskeletal injury. However, several practical and methodological aspects of US techniques should be considered when applying this technology in the elite sports context. Therefore, this narrative review aims to (1) present the principal US measures and field of applications in the context of elite sports; (2) to discuss, from a methodological perspective, the strengths and shortcomings of US imaging for the assessment of muscle and tendon properties; and (3) to provide future directions for research and application.

Alpine ski racing is known to be a sport with a high risk of injury and a high proportion of time-loss injuries. In recent years, substantial research efforts with regard to injury epidemiology, injury etiology, potential prevention measures, and measures’ evaluation have been undertaken. Therefore, the aims of this review of the literature were (i) to provide a comprehensive overview of what is known about the aforementioned four steps of injury prevention research in the context of alpine ski racing; and (ii) to derive potential perspectives for future research. In total, 38 injury risk factors were previously reported in literature; however, a direct relation to injury risk was proven for only five factors: insufficient core strength/core strength imbalance, sex (depending on type of injury), high skill level, unfavorable genetic predisposition, and the combination of highly shaped, short and wide skis. Moreover, only one prevention measure (i.e. the combination of less-shaped and longer skis with reduced profile width) has demonstrated a positive impact on injury risk. Thus, current knowledge deficits are mainly related to verifying the evidence of widely discussed injury risk factors and assessing the effectiveness of reasonable prevention ideas. Nevertheless, the existing knowledge should be proactively communicated and systematically implemented by sport federations and sport practitioners.

Background/aim In alpine ski racing, there is limited information about skiers’ mechanical characteristics and their relation to injury risk, in particular for World Cup (WC) competitions. Hence, current findings from epidemiological and qualitative research cannot be linked to skiers’ mechanics. This study was undertaken to investigate whether recently reported differences in numbers of injuries per 1000 runs for competition disciplines can be explained by differences in the skiers’ mechanics. Methods During seven giant slalom, four super-G and five downhill WC competitions, mechanical characteristics of a forerunner were captured using differential global navigation satellite technology and a precise terrain surface model. Finally, the discipline-specific skiers’ mechanics were compared with the respective number of injuries per hour skiing. Results While the number of injuries per hour skiing was approximately equal for all disciplines, kinetic energy, impulse, run time, turn radius and turn speed were significantly different and increased from giant slalom to super-G and downhill. Turn ground reaction forces were largest for giant slalom, followed by super-G and downhill. The number of jumps was doubled from super-G to downhill. Conclusions Associating the number of injuries per hour in WC skiing with skiers’ mechanical characteristics, injuries in super-G and downhill seem to be related to increased speed and jumps, while injuries in giant slalom may be related to high loads in turning. The reported differences in the number of injuries per 1000 runs might be explained by a bias in total exposure time per run and thus potentially by emerged fatigue.

In alpine ski racing the relationships between skier kinetics and kinematics and their effect on performance and injury-related aspects are not well understood. There is currently no validated system to determine all external forces simultaneously acting on skiers, particularly under race conditions and throughout entire races. To address the problem, this study proposes and assesses a method for determining skier kinetics with a single lightweight differential global navigation satellite system (dGNSS). The dGNSS kinetic method was compared to a reference system for six skiers and two turns each. The pattern differences obtained between the measurement systems (offset ± SD) were −26 ± 152 N for the ground reaction force, 1 ± 96 N for ski friction and −6 ± 6 N for the air drag force. The differences between turn means were small. The error pattern within the dGNSS kinetic method was highly repeatable and precision was therefore good (SD within system: 63 N ground reaction force, 42 N friction force and 7 N air drag force) allowing instantaneous relative comparisons and identification of discriminative meaningful changes. The method is therefore highly valid in assessing relative differences between skiers in the same turn, as well as turn means between different turns. The system is suitable to measure large capture volumes under race conditions.