Athlete Pose Estimation from Monocular TV Sports Footage

Fastovets, Mykyta; Guillemaut, Jean-Yves; Hilton, Adrian

doi:10.1109/cvprw.2013.152

Cited by 24 publications

(14 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Computer vision has become quite popular in analyzing athletes of different sport disciplines. [11] propose a userassisted method for estimating and tracking athlete poses from monocular TV sports footage. Their model is evaluated on hurdles and triple jump videos.…”

Section: Related Workmentioning

confidence: 99%

Robust Estimation of Flight Parameters for SKI Jumpers

Ludwig

Einfalt

Lienhart

2020

2020 IEEE International Conference on Multimedia &Amp; Expo Workshops (ICMEW)

View full text Add to dashboard Cite

This paper presents a model that robustly estimates important flight parameters for ski jumpers during their flight phase based on several camera views from the side along the jumpers' typical flight trajectories. A convolutional neural network for pose estimation, but also trained to detect skis, serves as a base model. It identifies 98.0% of the relevant flight parameters correctly within an angle threshold of 5 degrees, improving by 11.6% over previous work. In postprocessing, a pose checker first removes all wrong poses by using comparisons of distances and relative positions of the detected keypoints. A second step executes two RANSAC variants. One robustly estimates the average pose and another one the average pose angles. This model lifts the detection performance to 99.3% of the relevant flight parameters within a threshold of 5 degrees.

show abstract

Section: Related Workmentioning

confidence: 99%

Robust Estimation of Flight Parameters for SKI Jumpers

Ludwig

Einfalt

Lienhart

2020

2020 IEEE International Conference on Multimedia &Amp; Expo Workshops (ICMEW)

View full text Add to dashboard Cite

show abstract

“…Computer vision has been adopted for various applications in the sports domain. Prominent tasks include sports type [8] and activity recognition [17,27], tracking athletes and other objects of interest in videos [24,31] and human pose estimation [6,11]. [15] offer an overview of a wide range of application.…”

Section: Related Workmentioning

confidence: 99%

“…While most publications focus on human pose estimation on single 2D images, we are additionally interested in human pose estimation on videos. [6,34] use pictorial structures to model humans in videos. They extend the spatial interactions between body parts by temporal dependencies that describe the change of body part configurations over time.…”

Section: Related Workmentioning

confidence: 99%

Activity-Conditioned Continuous Human Pose Estimation for Performance Analysis of Athletes Using the Example of Swimming

Einfalt¹,

Zecha²,

Lienhart³

2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

In this paper we consider the problem of human pose estimation in real-world videos of swimmers. Swimming channels allow filming swimmers simultaneously above and below the water surface with a single stationary camera. These recordings can be used to quantitatively assess the athletes' performance. The quantitative evaluation, so far, requires manual annotations of body parts in each video frame. We therefore apply the concept of CNNs in order to automatically infer the required pose information. Starting with an off-the-shelf architecture, we develop extensions to leverage activity information -in our case the swimming style of an athlete -and the continuous nature of the video recordings. Our main contributions are threefold: (a) We apply and evaluate a fine-tuned Convolutional Pose Machine architecture as a baseline in our very challenging aquatic environment and discuss its error modes, (b) we propose an extension to input swimming style information into the fully convolutional architecture and (c) modify the architecture for continuous pose estimation in videos. With these additions we achieve reliable pose estimates with up to +16% more correct body joint detections compared to the baseline architecture.

show abstract

“…In generative approaches, pose estimation is formulated as an optimisation problem whose objective function is a discrepancy between a parametric prior body model and the input observation (Baak et al, 2013;Fastovets et al, 2013;Salzmann et al, 2007(for review, see Yang et al (2014)). This approach, however, suffers from local minima and solution multiplicity due to its often highly non-convex nature.…”

Section: Computer Vision and Machine Learning Approachesmentioning

confidence: 99%

A learning-based markerless approach for full-body kinematics estimation in-natura from a single image

Drory

Hartley

2017

Journal of Biomechanics

View full text Add to dashboard Cite

We present a supervised machine learning approach for markerless estimation of human full-body kinematics for a cyclist from an unconstrained colour image. This approach is motivated by the limitations of existing marker-based approaches restricted by infrastructure, environmental conditions, and obtrusive markers. By using a discriminatively learned mixture-of-parts model, we construct a probabilistic tree representation to model the configuration and appearance of human body joints. During the learning stage, a Structured Support Vector Machine (SSVM) learns body parts appearance and spatial relations. In the testing stage, the learned models are employed to recover body pose via searching in a test image over a pyramid structure. We focus on the movement modality of cycling to demonstrate the efficacy of our approach. In natura estimation of cycling kinematics using images is challenging because of human interaction with a bicycle causing frequent occlusions. We make no assumptions in relation to the kinematic constraints of the model, nor the appearance of the scene. Our technique finds multiple quality hypotheses for the pose. We evaluate the precision of our method on two new datasets using loss functions. Our method achieves a score of 91.1 and 69.3 on mean Probability of Correct Keypoint (PCK) measure and 88.7 and 66.1 on the Average Precision of Keypoints (APK) measure for the frontal and sagittal datasets respectively. We conclude that our method opens new vistas to robust user-interaction free estimation of full body kinematics, a prerequisite to motion analysis.

show abstract

Athlete Pose Estimation from Monocular TV Sports Footage

Cited by 24 publications

References 17 publications

Robust Estimation of Flight Parameters for SKI Jumpers

Robust Estimation of Flight Parameters for SKI Jumpers

Activity-Conditioned Continuous Human Pose Estimation for Performance Analysis of Athletes Using the Example of Swimming

A learning-based markerless approach for full-body kinematics estimation in-natura from a single image

Contact Info

Product

Resources

About