Three-Dimensional Body and Centre of Mass Kinematics in Alpine Ski Racing Using Differential GNSS and Inertial Sensors

Fasel, Benedikt; Spörri, Jörg; Gilgien, Matthias; Boffi, Geo; Chardonnens, Julien; Müller, Erich; Aminian, Kamiar

doi:10.3390/rs8080671

Cited by 63 publications

(91 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, we train S NSE + M NSE + R NSE with the standard views of S1 as strong supervision and with unlabeled examples from all the views-both standard and not-for S2 to S7. As shown in the bottom portion of Table 3, this greatly im- Generalization to new viewpoints through weak supervision (labeled S1, views [0, 2,4,7,8]; unlabeled S2 to S7, views 0-9; test on S8, views [1,3,5,6,9] proves the predictions for the novel views of S8 compared to using the supervised data only.…”

Section: Viewpoint Changes -Mpii-3dhpmentioning

confidence: 99%

Learning Monocular 3D Human Pose Estimation from Multi-view Images

Rhodin

Meyer

Spörri

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

256

244

View full text Add to dashboard Cite

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.would be to annotate video data. However, achieving high accuracy would require a great deal of annotation, which is tedious, slow, and error-prone. As illustrated by Fig. 1, we therefore propose to replace most of the annotations by the use of multiple views, at training time only. Specifically, we use them to provide weak supervision and force the system to predict the same pose in all views.While such view consistency constraints increase accuracy, they are unfortunately not sufficient. For example, the network can learn to always predict the same pose, independently of the input image. To prevent this, we use a small set of images with ground-truth poses, which serve a dual purpose. First, they provide strong supervision during training. Second, they let us regularize the multi-view predictions by encouraging them to remain close to the predictions of a network trained with the scarce supervised data only.In addition, we propose to use a normalized pose distance to evaluate all losses involving poses. It disentangles pose from scale, and we found it to be key to maintain accuracy when the annotated data is scarce.Our experiments demonstrate the effectiveness of our weakly-supervised multi-view training strategy on several 1 arXiv:1803.04775v2 [cs.CV]

show abstract

Section: Viewpoint Changes -Mpii-3dhpmentioning

confidence: 99%

Learning Monocular 3D Human Pose Estimation from Multi-view Images

Rhodin

Meyer

Spörri

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

256

244

View full text Add to dashboard Cite

show abstract

“…In addition we, analyze the mean absolute error (MAE) of skiing-specific metrics that are widely used in performance analysis [38,11], such as the center of mass (CoM), knee angle, and lean angle, where the latter is measured in the plane orthogonal to the skiing direction. These are defined formally in the supplementary material.…”

Section: Resultsmentioning

confidence: 99%

“…For the purpose of evaluating 3D pose estimation methods and comparing to related work, we used a manually annotated multi-view (MV-Ski) pan-tilt-zoom alpine skiing dataset [38,11,35]. It features 6 professional athletes on a Giant Slalom slope with three turns, filmed by six cameras that are arranged in a circle around the center of the track as shown in Figure 1.…”

Section: Related Workmentioning

confidence: 99%

“…This can be used to enhance the athlete's performance by comparing athletes and finding optimal motion trajectories. Existing methods, like optical barriers in skiing, only offer average speeds within segments, while other methods using Inertial Measurement Unit and/or GPS sensors [11,12,13,15,28] are cumbersome to wear. Using motion capture suits is also not feasible in high-speed settings with large capture volumes.…”

Section: Introductionmentioning

confidence: 99%

“…We focus on alpine skiing, where no suitable dataset exists. Existing alpine skiing datasets [38,11,35] are very limited in the number of athletes and locations that they feature, making methods trained on them not generalize well.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Motion Capture from Pan-Tilt Cameras with Unknown Orientation

Bachmann

Spörri

Fua

et al. 2019

2019 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

In sports, such as alpine skiing, coaches would like to know the speed and various biomechanical variables of their athletes and competitors. Existing methods use either body-worn sensors, which are cumbersome to setup, or manual image annotation, which is time consuming. We propose a method for estimating an athlete's global 3D position and articulated pose using multiple cameras. By contrast to classical markerless motion capture solutions, we allow cameras to rotate freely so that large capture volumes can be covered. In a first step, tight crops around the skier are predicted and fed to a 2D pose estimator network. The 3D pose is then reconstructed using a bundle adjustment method. Key to our solution is the rotation estimation of Pan-Tilt cameras in a joint optimization with the athlete pose and conditioning on relative background motion computed with feature tracking. Furthermore, we created a new alpine skiing dataset and annotated it with 2D pose labels, to overcome shortcomings of existing ones. Our method estimates accurate global 3D poses from images only and provides coaches with an automatic and fast tool for measuring and improving an athlete's performance.

show abstract

Multi-Phase Trajectory Optimization for Alpine Skiers Using an Improved Retractable Body Model

Cai,

Yao

2024

J Optim Theory Appl

View full text Add to dashboard Cite

Three-Dimensional Body and Centre of Mass Kinematics in Alpine Ski Racing Using Differential GNSS and Inertial Sensors

Cited by 63 publications

References 33 publications

Learning Monocular 3D Human Pose Estimation from Multi-view Images

Learning Monocular 3D Human Pose Estimation from Multi-view Images

Motion Capture from Pan-Tilt Cameras with Unknown Orientation

Multi-Phase Trajectory Optimization for Alpine Skiers Using an Improved Retractable Body Model

Contact Info

Product

Resources

About