Dataset for: Non-standard Squat Posture Detection Method Using Human Skeleton
Abstract
This dataset contains processed skeletal keypoint 2D coordinates and joint angles (hip and knee) extracted using the MediaPipe framework. It includes data from three types of squat postures: standard squats, shallow squats, and good morning squats, performed by 22 subjects. The dataset is specifically designed for validating lightweight squat posture detection and biomechanical analysis algorithms. To protect subject privacy and comply with ethical restrictions, raw video recordings are excluded from this repository.
Fields of Study & Subjects
Human Pose and Action Recognition
Ergonomics and Musculoskeletal Disorders
Context-Aware Activity Recognition Systems
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 4 March 2026
- Language
- EN
- Document type
- Dataset