A Systematic Review of the Application of Camera-Based Human Pose Estimation in the Field of Sport and Physical Exercise

Human Pose Estimation (HPE) has received considerable attention during the past years, improving its performance thanks to the use of Deep Learning, and introducing new interesting uses, such as its application in Sport and Physical Exercise (SPE). The aim of this systematic review is to analyze the literature related to the application of HPE in SPE, the available data, methods, performance, opportunities, and challenges. One reviewer applied different inclusion and exclusion criteria, as well as quality metrics, to perform the paper filtering through the paper databases. The Association for Computing Machinery Digital Library, Web of Science, and dblp included more than 500 related papers after the initial filtering, finally resulting in 20. In addition, research was carried out regarding the publicly available data related to this topic. It can be concluded that even if related public data can be found, much more data is needed to be able to obtain good performance in different contexts. In relation with the methods of the authors, the use of general purpose systems as base, such as Openpose, combined with other methods and adaptations to the specific use case can be found. Finally, the limitations, opportunities, and challenges are presented.

Download Full-text

3D Human Pose Estimation Using Spatio-Temporal Networks with Explicit Occlusion Training

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6689 ◽

2020 ◽

Vol 34 (07) ◽

pp. 10631-10638

Author(s):

Yu Cheng ◽

Bo Yang ◽

Bo Wang ◽

Robby T. Tan

Keyword(s):

Pose Estimation ◽

Ground Truth ◽

Video Data ◽

Training Data ◽

Human Pose Estimation ◽

Ground Truth Data ◽

Public Data ◽

Spatio Temporal ◽

Human Pose ◽

3D Human Pose Estimation

Estimating 3D poses from a monocular video is still a challenging task, despite the significant progress that has been made in the recent years. Generally, the performance of existing methods drops when the target person is too small/large, or the motion is too fast/slow relative to the scale and speed of the training data. Moreover, to our knowledge, many of these methods are not designed or trained under severe occlusion explicitly, making their performance on handling occlusion compromised. Addressing these problems, we introduce a spatio-temporal network for robust 3D human pose estimation. As humans in videos may appear in different scales and have various motion speeds, we apply multi-scale spatial features for 2D joints or keypoints prediction in each individual frame, and multi-stride temporal convolutional networks (TCNs) to estimate 3D joints or keypoints. Furthermore, we design a spatio-temporal discriminator based on body structures as well as limb motions to assess whether the predicted pose forms a valid pose and a valid movement. During training, we explicitly mask out some keypoints to simulate various occlusion cases, from minor to severe occlusion, so that our network can learn better and becomes robust to various degrees of occlusion. As there are limited 3D ground truth data, we further utilize 2D video data to inject a semi-supervised learning capability to our network. Experiments on public data sets validate the effectiveness of our method, and our ablation studies show the strengths of our network's individual submodules.

Download Full-text

GYM REP TRACKER USING MEDIAPIPE AND PYTHON

International journal of multidisciplinary advanced scientific research and innovation ◽

10.53633/ijmasri.2021.1.10.001 ◽

2021 ◽

Vol 1 (10) ◽

pp. 240-245

Author(s):

Rahul Ratusaria ◽

Tushar Baghel ◽

Ayush Chander Vanshi ◽

Neeraj Garg

Keyword(s):

Real Time ◽

Pose Estimation ◽

Human Pose Estimation ◽

Suitable Model ◽

The Past ◽

Key Points ◽

Intelligence Models ◽

Artificial Intelligence Models ◽

Human Pose ◽

Computational Resources

Human Pose estimation has grabbed the eye of the computer vision community for the past few decades. It is a vital step closer to knowledge people in pics and motion pictures. Strong articulations, small and hardly visible joints, occlusions, apparel, and lighting changes make it very difficult to perform estimate pose. Human Pose estimation is an important problem that needed to be study. It is used to detect human anatomical key points (e.g., shoulder, elbows, legs, wrist, etc.) in real time using less computational resources. There are many Artificial Intelligence models i.e, Posenet, OpenPose1 and MediaPipe8 for Real time Human Pose Estimation. Many experiments has performed to find out the best suitable model for Human Pose Estimation. Experiments stated that PoseNet is suitable to run on lightweight devices like browsers whereas OpenPose meant to run on GPU powered devices and is more accurate. On the other hand, MediaPipe is very fast, modular, reusable and highly efficient. Hence, our model uses the MediaPipe to perform its estimation. Keywords: Pose estimation, Gym Rep Tracker, Media Pipe, Python, Machine learning

Download Full-text

Yoga Posture Classification using Computer Vision

International Journal of Engineering and Management Research ◽

10.31033/ijemr.11.4.11 ◽

2021 ◽

Vol 11 (4) ◽

Author(s):

Madhura Prakash ◽

Aishwarya S ◽

Disha Maru ◽

Naman Chandra ◽

Varshini V ◽

...

Keyword(s):

Computer Vision ◽

Pose Estimation ◽

Confidence Score ◽

Human Pose Estimation ◽

Computer Assisted ◽

The Past ◽

The World ◽

Human Pose ◽

The One ◽

Video Input

There has been over the past few years, a very increased popularity for yoga. A lot of literatures have been published that claim yoga to be beneficial in improving the overall lifestyle and health especially in rehabilitation, mental health and more. Considering the fast-paced lives that individuals live, people usually prefer to exercise or work-out from the comfort of their homes and with that a need for an instructor arises. Hence why, we have developed a self-assisted system which can be used to detect and classify yoga asanas, which is discussed in-depth in this paper. Especially now when the pandemic has taken over the world, it is not feasible to attend physical classes or have an instructor over. Using the technology of Computer Vision, a computer-assisted system such as the one discussed, comes in very handy. The technologies such as ml5.js, PoseNet and Neural Networks are made use for the human pose estimation and classification. The proposed system uses the above-mentioned technologies to take in a real-time video input and analyze the pose of an individual, and classifies the poses into yoga asanas. It also displays the name of the yoga asana that is detected along with the confidence score.

Download Full-text

Human pose, hand and mesh estimation using deep learning: a survey

The Journal of Supercomputing ◽

10.1007/s11227-021-04184-7 ◽

2022 ◽

Author(s):

Mukhiddin Toshpulatov ◽

Wookey Lee ◽

Suan Lee ◽

Arousha Haghighian Roudsari

Keyword(s):

Computer Vision ◽

Deep Learning ◽

Pose Estimation ◽

State Of The Art ◽

Significant Problem ◽

Estimation Methods ◽

Human Pose Estimation ◽

Estimation Techniques ◽

The Past ◽

Human Pose

AbstractHuman pose estimation is one of the issues that have gained many benefits from using state-of-the-art deep learning-based models. Human pose, hand and mesh estimation is a significant problem that has attracted the attention of the computer vision community for the past few decades. A wide variety of solutions have been proposed to tackle the problem. Deep Learning-based approaches have been extensively studied in recent years and used to address several computer vision problems. However, it is sometimes hard to compare these methods due to their intrinsic difference. This paper extensively summarizes the current deep learning-based 2D and 3D human pose, hand and mesh estimation methods with a single or multi-person, single or double-stage methodology-based taxonomy. The authors aim to make every step in the deep learning-based human pose, hand and mesh estimation techniques interpretable by providing readers with a readily understandable explanation. The presented taxonomy has clearly illustrated current research on deep learning-based 2D and 3D human pose, hand and mesh estimation. Moreover, it also provided dataset and evaluation metrics for both 2D and 3DHPE approaches.

Download Full-text