2026-08-25T22:11:04Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/4578 2021-12-13T06:18:57Z 1582963302567:1597824251561 user-ucsy

Effective Multi-View for Human Activity Recognition on Skeletal Model Win, Sandar Thein, Thin Lai Lai The recognition of 3D human pose from 2D joint location is fundamental to numerous visionissues in analysis of video sequences. Various methods using with skeletal model have been described in pastdecades, but there is required a powerful system with stable and reliable manner in activity recognitionbecause video sequences can contain different people that may be any position or scale and complex spatialinterference. With the development of deep learning, skeleton-based human representation is more reliableto motion speed and appearance of human body scale. Skeleton data contains compact information of themajor body joints and that support multi-view to human activity recognition. To satisfy our aim, the proposedsystem is developed by using OpenPose detector that achieve effective results for 2D pose and DeepLearning based approach. Our goal is to extract valuable information between human joints and to recognizecorrect activity from human representation in video sequences. 2020-02-28 http://hdl.handle.net/20.500.12678/0000004578 https://meral.edu.mm/records/4578