Posture evaluation for variants of weight-lifting workouts recognition

Ng, Jiunn (2020) Posture evaluation for variants of weight-lifting workouts recognition. Final Year Project, UTAR.

Preview

PDF Download (6Mb) | Preview

Abstract

Weight lifting is a flow of body movement pack in an organized exercise to force the body muscles to contract under tension by using weights such as barbells, dumbbells or even body weights in order to trigger growth, strength, endurance and power. Performing wrong posture is a very common issue for every gymnast, either beginner or even professional. Computer Vision (CV) is a field of computer science that seeks to develop techniques in enabling computers to see, identify, understand and process the content of digital images in the same way that human vision does, then provide appropriate output. Object detection and object recognition, which are two of the famous CV technologies, have been applied in this project. Posture performing workout will be detected then evaluate the posture. KNN classifier has been trained from calculating angles between joint keypoints of the user to recognise the workout type. The system with the function of detect and recognize the workout type from the input video had been tested with multiple workout type under different environments and achieved around 98% accuracy. The system is also able to classify different types of improper posture with the accuracy of 80.69% for Bicep Curl class, 65.35% for Front Raise class and 89.75% for Shoulder Press class.

Actions (login required)