Skip to main content
European Commission logo
English English
CORDIS - EU research results
CORDIS
CORDIS Web 30th anniversary CORDIS Web 30th anniversary

A Robust, Real-time, and 3D Human Motion Capture System through Multi-Cameras and AI

Project description

Welcome to real-time and markerless 3D motion tracking

Advancements in human motion tracking technology mean that it is now possible to capture and record the movements of a person in three-dimensional space in real time. This involves using only external cameras (and no additional markers) to track the position, orientation and movements of various body parts as a person moves. This technology finds applications in diverse fields such as healthcare, entertainment, industry and sports, contributing to areas like virtual reality, biomechanics analysis, animation and more. In this context, the ERC-funded Real-Move project aims to address the limitations of existing motion capture systems, enhancing accuracy and efficiency in tracking human motion. In addition to motion tracking, the project will make strides in workplace safety, potentially saving billions in economic losses.

Objective

The ability to reliably track 3D human motion in real-time is crucial for a wide range of applications across various fields, such as healthcare, entertainment, industry, and sports. Occupational ergonomics, as the intersection of industry and healthcare, could particularly benefit from such a solution, as recent reports indicate that physical and cognitive ergonomics issues at work contribute to major economic losses in Europe. However, the existing commercial human motion capture (MoCap) systems often exploit multiple markers or inertial measurement units (IMUs), which, in addition to their high costs, suffer from many technical and usability issues. These include lengthy set-up times, compromised user comfort and bothersome wearability needs, and in case of IMU based Mo-Cap systems, large drifts and inaccuracies over time. Some of these issues can be dealt with by using vision-based human skeletal trackers, however, high vulnerability to occlusions, and often, the missing or inaccurate 3D tracking capacity have severely depreciated their reliability-of-use for real-world applications. These leave us with no existing market solutions for marker-less (comfortable), robust, economic, and real-time 3D human motion tracking. Real-Move aims to create such a solution by exploiting multi-camera views and AI algorithms. The system will be capable of tracking multiple people in the scene with high accuracy and, in addition to motion tracking data, be able to provide application-driven data services such as human factors. Real-Move has the highest innovation potential to become a key player in the multi-Billion Euros MoCap and workplace safety markets. In addition, by providing quick and easy access to vision-based risk monitoring tools, it can make a huge socio-economic impact by improving the quality of life of the individuals at work while saving a large amount of money by cutting waste.

Fields of science (EuroSciVoc)

CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques.

You need to log in or register to use this function

Host institution

FONDAZIONE ISTITUTO ITALIANO DI TECNOLOGIA
Net EU contribution
€ 150 000,00
Address
VIA MOREGO 30
16163 Genova
Italy

See on map

Region
Nord-Ovest Liguria Genova
Activity type
Research Organisations
Links
Total cost
No data

Beneficiaries (1)