| 1. |
- Yamazaki, Junya, et al.
(författare)
-
Analysis of a Severe Head Injury in World Cup Alpine Skiing : A Case Report.
- 2015
-
Ingår i: Medicine & Science in Sports & Exercise. - 0195-9131 .- 1530-0315. ; 47:6, s. 1113-1118
-
Tidskriftsartikel (refereegranskat)abstract
- Traumatic brain injury (TBI) is the leading cause of death in alpine skiing. It has been found that helmet use can reduce the incidence of head injuries between 15% and 60%. However, knowledge on optimal helmet performance criteria in World Cup alpine skiing is currently limited owing to the lack of biomechanical data from real crash situations. Purpose: This study aimed to estimate impact velocities in a severe TBI case in World Cup alpine skiing. Methods: Video sequences from a TBI case in World Cup alpine skiing were analyzed using a model-based image matching technique. Video sequences from four camera views were obtained in full high-definition (1080p) format. A three-dimensional model of the course was built based on accurate measurements of piste landmarks and matched to the background video footage using the animation software Poser 4. A trunk-neck-head model was used for tracking the skier's trajectory. Results: Immediately before head impact, the downward velocity component was estimated to be 8 m.s(-1). After impact, the upward velocity was 3 m.s(-1), whereas the velocity parallel to the slope surface was reduced from 33 m.s(-1) to 22 m.s(-1). The frontal plane angular velocity of the head changed from 80 radIsj1 left tilt immediately before impact to 20 rad.s(-1) right tilt immediately after impact. Conclusions: A unique combination of high-definition video footage and accurate measurements of landmarks in the slope made possible a high-quality analysis of head impact velocity in a severe TBI case. The estimates can provide crucial information on how to prevent TBI through helmet performance criteria and design.
|
|
| 2. |
- Zwölfer, Michael, et al.
(författare)
-
A graph-based approach can improve keypoint detection of complex poses: a proof-of-concept on injury occurrences in alpine ski racing
- 2023
-
Ingår i: Scientific Reports. - : Nature Publishing Group. - 2045-2322. ; 13:1
-
Tidskriftsartikel (refereegranskat)abstract
- For most applications, 2D keypoint detection works well and offers a simple and fast tool to analyse human movements. However, there remain many situations where even the best state-of-the-art algorithms reach their limits and fail to detect human keypoints correctly. Such situations may occur especially when individual body parts are occluded, twisted, or when the whole person is flipped. Especially when analysing injuries in alpine ski racing, such twisted and rotated body positions occur frequently. To improve the detection of keypoints for this application, we developed a novel method that refines keypoint estimates by rotating the input videos. We select the best rotation for every frame with a graph-based global solver. Thereby, we improve keypoint detection of an arbitrary pose estimation algorithm, in particular for 'hard' keypoints. In the current proof-of-concept study, we show that our approach outperforms standard keypoint detection results in all categories and in all metrics, in injury-related out-of-balance and fall situations by a large margin as well as previous methods, in performance and robustness. The Injury Ski II dataset was made publicly available, aiming to facilitate the investigation of sports accidents based on computer vision in the future.
|
|
