Using Richer Models for Articulated Pose Estimation of Footballers

Kazemi, Vahid; Sullivan, Josephine

doi:10.5244/c.26.6

Cited by 13 publications

(10 citation statements)

References 17 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This class of methods are attractive as they enable efficient inference by reducing the conditional dependencies between parts, and demand less labeled training data as they can generate new poses at test time. Part-based models have also been used for 3D pose estimation [2,4,13,17,19], but to our knowledge good performance has only been reported in studio environments. In this paper we focus on computing efficient and accurate 3D part appearance likelihoods that can be plugged into any 3D part-based model.…”

Section: Introductionmentioning

confidence: 99%

Multi-view Body Part Recognition with Random Forests

Kazemi¹,

Burénius²,

Azizpour³

et al. 2013

Procedings of the British Machine Vision Conference 2013

Self Cite

101

View full text Add to dashboard Cite

This paper addresses the problem of human pose estimation, given images taken from multiple dynamic but calibrated cameras. We consider solving this task using a part-based model and focus on the part appearance component of such a model. We use a random forest classifier to capture the variation in appearance of body parts in 2D images. The result of these 2D part detectors are then aggregated across views to produce consistent 3D hypotheses for parts. We solve correspondences across views for mirror symmetric parts by introducing a latent variable. We evaluate our part detectors qualitatively and quantitatively on a dataset gathered from a professional football game.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-view Body Part Recognition with Random Forests

Kazemi¹,

Burénius²,

Azizpour³

et al. 2013

Procedings of the British Machine Vision Conference 2013

Self Cite

101

View full text Add to dashboard Cite

show abstract

“…However, they used a random forest classifier which has the advantages of capturing the variation in the appearance of body parts in 2D images. In the other work by Kazemi [15], the flexible mixture of parts (FMP) model [26] was employed to detect body parts in the images. In the mentioned works by Kazemi and Burenius [5,15,16], calibration information is known and no temporal information is exploited.…”

Section: Related Workmentioning

confidence: 99%

Pose estimation of soccer players using multiple uncalibrated cameras

Afrouzian

Seyedarabi

Kasaei

2015

Multimed Tools Appl

View full text Add to dashboard Cite

Fully automatic algorithm for estimating the 3D human pose from multiple uncalibrated cameras is presented. Unlike the state-of-the-art methods which use the estimated pose of previous frames to restrict the candidates of current frame, the proposed method uses the viewpoint of previous frame in order to obtain an accurate pose. This paper also introduces a method to incorporate pose estimation results of several cameras without using the calibration information. The algorithm employs a rich descriptor for matching purposes. The performance of the proposed method is evaluated on a soccer database which is captured by multiple cameras. The dataset of silhouettes, in which the related 3D skeleton poses are known, is also constructed. Experimental results show that the proposed algorithm has a high accuracy rate in estimation of 3D pose of soccer players.

show abstract

“…In contrast, the evaluation of dynamic events has been studied only for single exercises and sub-joints [23]. Existing annotated 2D datasets deal with either images [30] or deal with a small variety of activities [31,32].…”

Section: Keypoint Confidence Extractionmentioning

confidence: 99%

Single Camera-Based Remote Physical Therapy: Verification on a Large Video Dataset

et al. 2022

View full text Add to dashboard Cite

In recent years, several systems have been developed to capture human motion in real-time using common RGB cameras. This approach has great potential to become widespread among the general public as it allows the remote evaluation of exercise at no additional cost. The concept of using these systems in rehabilitation in the home environment has been discussed, but no work has addressed the practical problem of detecting basic body parts under different sensing conditions on a large scale. In this study, we evaluate the ability of the OpenPose pose estimation algorithm to perform keypoint detection of anatomical landmarks under different conditions. We infer the quality of detection based on the keypoint confidence values reported by the OpenPose. We used more than two thousand unique exercises for the evaluation. We focus on the influence of the camera view and the influence of the position of the trainees, which are essential in terms of the use for home exercise. Our results show that the position of the trainee has the greatest effect, in the following increasing order of suitability across all camera views: lying position, position on the knees, sitting position, and standing position. On the other hand, the effect of the camera view was only marginal, showing that the side view is having slightly worse results. The results might also indicate that the quality of detection of lower body joints is lower across all conditions than the quality of detection of upper body joints. In this practical overview, we present the possibilities and limitations of current camera-based systems in telerehabilitation.

show abstract

Using Richer Models for Articulated Pose Estimation of Footballers

Cited by 13 publications

References 17 publications

Multi-view Body Part Recognition with Random Forests

Multi-view Body Part Recognition with Random Forests

Pose estimation of soccer players using multiple uncalibrated cameras

Single Camera-Based Remote Physical Therapy: Verification on a Large Video Dataset

Contact Info

Product

Resources

About