A comprehensive survey on human pose estimation approaches

Dubey, Shradha; Dixit, Manish

doi:10.1007/s00530-022-00980-0

Cited by 34 publications

(11 citation statements)

References 114 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On account of recorded recordings, this progression happens offline, though for continuous forecasts, it happens web based utilizing contribution from the camera to flexibly keypoints to the proposed model. OpenPose is an opensource library for multi-individual keypoint location, which recognizes the human body, hand, and facial keypoints together [12]. The places of 18 keypoints followed by the OpenPose, For example ears, eyes, nose, neck, shoulders, hips, knees, lower legs, elbows, and wrists.…”

Section: Methodsmentioning

confidence: 99%

Advancing Yoga Practice : Leveraging Opencv and Mediapipe for Pose Detection

2024

IRJMETS

View full text Add to dashboard Cite

Yoga is a centuries-old practice that has become more popular all over the world due to its benefits for the body, mind, and spirit [1]. Nowadays, yoga is a popular kind of fitness all around the world. Proper posture is the cornerstone of yoga. Despite all of yoga's health benefits, bad posture can cause problems including sprains and soreness in the muscles. Over the past few years, working remotely has drawn more interest from people than working in person. Our approach is beneficial to people who are used to living online and struggle to find the time to visit yoga facilities. An increasing number of people are interested in automating the analysis of yoga postures in order to improve practitioners' performance and knowledge of the poses as a result of technological integration. Our technique is used by the suggested system to accurately extract features and estimate pose from input photos or video frames. The model classifies the yoga positions using our system's web cameras, and the image is used as input. The asana is improved by enhancing the input derived from the yoga postures through the application of multiple deep learning models.

show abstract

Section: Methodsmentioning

confidence: 99%

Advancing Yoga Practice : Leveraging Opencv and Mediapipe for Pose Detection

2024

IRJMETS

View full text Add to dashboard Cite

show abstract

“…Dubey and Dixit reviewed the key research and recent advances in human pose estimation, including 2D and 3D pose estimation techniques and their traditional and deep learning methods. The results showed that these different pose assessment methods effectively improved the accuracy and efficiency of pose prediction [6]. Liu et al proposed a lightweight pose estimation network using the polarimetric self-attention mechanism.…”

Section: Related Workmentioning

confidence: 99%

“…This is because there is semantic information shared between key points, and later stages can optimize detection results based on the information extracted from previous stages [28]. Each network branch can be iterated, with the next branch using information from the previous stage as input to make predictions, as shown in equation (6).…”

Section: Construction and System Design Of Basketball Fixed-point Sho...mentioning

confidence: 99%

Basketball Fixed-point Shot Hit Prediction Based on Human Pose Estimation Algorithm

Li,

Hua

2024

IJCAI

View full text Add to dashboard Cite

As computer vision and artificial intelligence develop, the research on basketball fixed-point shooting hit prediction based on human pose estimation algorithm becomes a topic of great concern. To construct a basketball fixed-point shooting hit prediction model, a new object detection algorithm was designed, and the You Only Look Once version 5 algorithm was optimized on the basis of GIoU loss function and Convolutional Block Attention Module. Then, a new human pose estimation algorithmwas designed based on the OpenPose algorithm. Results showed that the average accuracy of the improved YOLOv5 algorithm reached 95.34% when the number of iterations was 50. In the comparison among improved OpenPose and other algorithms, improved OpenPose performed better, with a recall rate of 96.23%, an accuracy of 87.16%, a precision of 89.75%, and an F1 value of 88.19%. In the comparison with other models, the area of receiver operating characteristic curve was the largest, reaching 0.974, and the F1 value, accuracy and recall rate of the research model were the highest, reaching 95.54%, 96.39% and 98.25%, respectively. Results show that it effectively predicts the shoot hit of basketball fixed-point shooting, which provides a useful reference for tactical analysis and player performance evaluation in basketball games.Povzetek: Raziskava predstavlja napovedni model za zadetke pri košarkarskem metu s fiksne točke na osnovi algoritma za ocenjevanje človeške drže, kar je koristno za taktično analizo in ocenjevanje igralcev v košarki.

show abstract

“…The label serial number is assigned to each image in the order of motion, with each exercise repeated 4-5 times within 32 frames. The total frame count for each exercise ranges from 50,000 to 260,000, calculated based on the number of motion states, models, cameras (5), and one cycle frame (32).…”

Section: Dataset Preparation and Definition Of Each Exercisementioning

confidence: 99%

“…A crucial aspect of HPE is feature extraction from the input signal, and various models have been developed for this purpose, including skeleton-based, contour-based, and volume-based models. The skeleton-based model, which connects key points corresponding to human joints, is the most widely used [ 5 ]. The posture could be represented by key-point (x, y, z) coordinates in the skeleton model, and these coordinates could be used for posture recognition [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Automated Machine Learning Platforms for Exercise Anthropometry-Based Typology Analysis: Performance Evaluation of AWS SageMaker, GCP VertexAI, and MS Azure

Choi

Choi²,

Heo

2023

Bioengineering

View full text Add to dashboard Cite

The increasing prevalence of machine learning (ML) and automated machine learning (AutoML) applications across diverse industries necessitates rigorous comparative evaluations of their predictive accuracies under various computational environments. The purpose of this research was to compare and analyze the predictive accuracy of several machine learning algorithms, including RNNs, LSTMs, GRUs, XGBoost, and LightGBM, when implemented on different platforms such as Google Colab Pro, AWS SageMaker, GCP Vertex AI, and MS Azure. The predictive performance of each model within its respective environment was assessed using performance metrics such as accuracy, precision, recall, F1-score, and log loss. All algorithms were trained on the same dataset and implemented on their specified platforms to ensure consistent comparisons. The dataset used in this study comprised fitness images, encompassing 41 exercise types and totaling 6 million samples. These images were acquired from AI-hub, and joint coordinate values (x, y, z) were extracted utilizing the Mediapipe library. The extracted values were then stored in a CSV format. Among the ML algorithms, LSTM demonstrated the highest performance, achieving an accuracy of 73.75%, precision of 74.55%, recall of 73.68%, F1-score of 73.11%, and a log loss of 0.71. Conversely, among the AutoML algorithms, XGBoost performed exceptionally well on AWS SageMaker, boasting an accuracy of 99.6%, precision of 99.8%, recall of 99.2%, F1-score of 99.5%, and a log loss of 0.014. On the other hand, LightGBM exhibited the poorest performance on MS Azure, achieving an accuracy of 84.2%, precision of 82.2%, recall of 81.8%, F1-score of 81.5%, and a log loss of 1.176. The unnamed algorithm implemented on GCP Vertex AI showcased relatively favorable results, with an accuracy of 89.9%, precision of 94.2%, recall of 88.4%, F1-score of 91.2%, and a log loss of 0.268. Despite LightGBM’s lackluster performance on MS Azure, the GRU implemented in Google Colab Pro displayed encouraging results, yielding an accuracy of 88.2%, precision of 88.5%, recall of 88.1%, F1-score of 88.4%, and a log loss of 0.44. Overall, this study revealed significant variations in performance across different algorithms and platforms. Particularly, AWS SageMaker’s implementation of XGBoost outperformed other configurations, highlighting the importance of carefully considering the choice of algorithm and computational environment in predictive tasks. To gain a comprehensive understanding of the factors contributing to these performance discrepancies, further investigations are recommended.

show abstract

A comprehensive survey on human pose estimation approaches

Cited by 34 publications

References 114 publications

Advancing Yoga Practice : Leveraging Opencv and Mediapipe for Pose Detection

Advancing Yoga Practice : Leveraging Opencv and Mediapipe for Pose Detection

Basketball Fixed-point Shot Hit Prediction Based on Human Pose Estimation Algorithm

A Comparative Study of Automated Machine Learning Platforms for Exercise Anthropometry-Based Typology Analysis: Performance Evaluation of AWS SageMaker, GCP VertexAI, and MS Azure

Contact Info

Product

Resources

About