Results 121 to 130 of about 3,732 (210)

Advancing Artistic Swimming Officiating and Performance Assessment: A Computer Vision Study Using MediaPipe

International Journal of Computer Science in Sport
Artistic Swimming (AS) requires complete execution and synchronization of movements for performance evaluation. The interest in objective and subjective performance analysis worldwide in sports via valid and reliable Artificial Intelligence (AI) tools is
Edriss Saeid, Caprioli Lucio, Campoli Francesca, Manzi Vincenzo, Padua Elvira, Bonaiuto Vincenzo, Romagnoli Cristian, Annino Giuseppe   +7 more
doaj   +1 more source

Optimizing Hand Region Detection in MediaPipe Holistic Full-Body Pose Estimation to Improve Accuracy and Avoid Downstream Errors

This paper addresses a critical flaw in MediaPipe Holistic's hand Region of Interest (ROI) prediction, which struggles with non-ideal hand orientations, affecting sign language recognition accuracy.
Moryossef, Amit
core  

Development and implementation of a MediaPipe-based AI teaching-learning model in school physical education for health promotion

Frontiers in Public Health
IntroductionArtificial intelligence (AI) technologies are increasingly used in school physical education (PE) to provide real-time feedback and support instruction that promotes youth physical activity and health. However, many AI applications remain top-
Donghyun Kim, Yongchul Kwon, Gunsang Cho, Minseo Kang   +3 more
doaj   +1 more source

AI Robotic Arm with Hand Tracking [PDF]

This project aims to build a robotic arm with artificial intelligence. Implementation methods included building a 3D-printed forearm, writing a Python program with OpenCV and MediaPipe to read the webcam footage and give the Arduino Uno a command ...
Piascik, Julia
core   +1 more source

EgoBlur: Responsible Innovation in Aria

, 2023
Project Aria pushes the frontiers of Egocentric AI with large-scale real-world data collection using purposely designed glasses with privacy first approach.
Gupta, Prince, Meissner, Jeff, Miglani, Sagar, Miller, Edward, Newcombe, Richard, Parkhi, Omkar M, Pesqueira, Luis, Prasad, Ishita, Raina, Nikhil, Ren, Carl, Saarinen, Steve, Schwesinger, Mark, Somasundaram, Guruprasad, Yan, Mingfei, Zheng, Kang   +14 more
core  

Deep Learning Based Technical Classification of Badminton Pose with Convolutional Neural Networks

Ilkom Jurnal Ilmiah
This research aims to identify and categorize badminton strategies using a Convolutional Neural Network (CNN) model combined with BlazePose architecture and Mediapipe Pose Solution tools, yielding understandable and practical results.
Tukino Tukino, Mutiana Pratiwi, Sarjon Defit   +2 more
doaj   +1 more source

Japanese fingerspelling identification by using MediaPipe

Nonlinear Theory and Its Applications, IEICE, 2022
Masanao Yasumuro, Kenya Jin'no
openaire   +1 more source

VIDEO SKELETONIZATION AND AI: A NOVEL APPROACH FOR ANALYZING KINEMATICS IN TABLE TENNIS [PDF]

This study introduces a simple yet effective system to measure table tennis player movements and relate them to the moment the ball hits the racket.
Abeni, Nicola, Ferlinghetti, Enrico, Kumamoto, Ryushi, Lancini, Matteo, LOH, Ping Yeap   +4 more
core   +1 more source

Real-Time Norwegian Sign Language Recognition Using MediaPipe and LSTM [PDF]

The application of machine learning models for sign language recognition (SLR) is a well-researched topic. However, many existing SLR systems focus on widely used sign languages, e.g., American Sign Language, leaving other underrepresented sign languages
Boletsis, Costas, Rudshavn, Pål, Uddin, Md Zia   +2 more
core   +1 more source

Annotated Hands for Generative Models

Generative models such as GANs and diffusion models have demonstrated impressive image generation capabilities. Despite these successes, these systems are surprisingly poor at creating images with hands.
Gandhi, Atith N, Turk, Greg, Yang, Yue
core