About us
Espace utilisateur
Education
INSTN offers more than 40 diplomas from operator level to post-graduate degree level. 30% of our students are international students.
Professionnal development
Professionnal development
Find a training course
INSTN delivers off-the-self or tailor-made training courses to support the operational excellence of your talents.
Human capital solutions
At INSTN, we are committed to providing our partners with the best human capital solutions to develop and deliver safe & sustainable projects.
Thesis
Home   /   Thesis   /   Human motion generation and dataset creation using AI techniques for human action recognition in an industrial context

Human motion generation and dataset creation using AI techniques for human action recognition in an industrial context

Engineering sciences Mathematics - Numerical analysis - Simulation Numerical simulation Technological challenges

Abstract

In the context of industry 4.0, the analysis, recognition and prediction of human actions is becoming more important for decision-making and fluid and intuitive human-machine interaction. However, human action recognition requires large datasets to train deep learning architectures. The aim of the thesis is to generate, for industrial use cases, large motion datasets thanks to digital human animation, starting with a reduced number of motion capture samples from mixed reality simulations. These datasets will be used to train action recognition architectures, for industrial applications on human-machine interaction, assembly worksheets generation, and ergonomics evaluation.

Laboratory

Département Intelligence Ambiante et Systèmes Interactifs (LIST)
Service Interactions et Réseaux
Laboratoire de Simulation Interactive
HESAM Université
Top envelopegraduation-hatlicensebookuserusersmap-markercalendar-fullbubblecrossmenuarrow-down