News

WHY BET ON COMPUTER VISION?

By Dr. Pierre Plantard CTO de Moovency

In recent years, you have heard more and more about "Artificial Intelligence" (AI), "Deep Learning" or "Big Data". The underlying concepts of these IT disciplines are not always easy to understand but impact your professional daily life. At Moovency, we offer the AI-based KIMEA tool, which improves the analysis of risky postures that can cause musculoskeletal disorders (MSDs) in industries. Our approach, based on a single camera, is about its simplicity of use and its performance. Gone are the tedious placement of twenty sensors on the worker's body, no more complex training in human anatomy and technology, and no more frequent calibration phases of the system that disrupt the production line. We've been betting on AI technologies applied to computer vision for several years now and we're explaining why.

AI, Deep Learning and Computer Vision

Computer vision allows your machine to spot humans in images filmed by a camera and determine the positions of each 3D joints. To do this, your computer uses models to deduce these postures from the images you give him Give. These algorithms learn from a lot of data for example, this is called deep learning or "Deep learning" learning."

During our research activities, prior to the creation of Moovency, we studied computer-based computer vision technology based on the KINECT camera Microsoft. This technology, from the world of video games, allowed to obtain a person's 3D postures without having to put sensors or sensors on them a combination on the body. Although promising, this technology suffered limits such as the low accuracy of postures when obscuring the field of view by objects. We had then developed algorithms specific to the constraints of the industrial world, we sufficient accuracy for a measure in condition of the real work.

Validated both in the laboratory and on production site, as in our partner Faurecia, the results were published in a scientific journal of reference of the field and available for free here. Although our research has allowed us to use KIMEA in many industrial areas, some usage constraints have yet to be addressed. The main constraint was to place the camera securely and in front of the measured worker, which was not always possible.

That's why we developed KIMEA 360. These algorithms from "Deep "latest generation of learning" allow you to measure the posture of the your workers from the front as well as from the back. In addition, our solution allows you to to follow the worker with a mobile camera, which addresses the limits to have a fixed point of view. This innovation takes us to the next level important, allowing us to offer you a portable and non-invasive tool compatible the majority of industrial use cases.

example of computer vision

All these innovations are the result of the recent development of AI and in particular the "deep learning" methods applied to computer vision. There are many future developments in the field, and we offer great prospects to make you even easier use and business functionality.

Other technologies available?

You probably need to know other older technologies as well used to measure workers' postures and associated risks.

These are inertial sensors (IMUs) that measure their own orientations over time. Although resistant to occultations and beyond the constraints of use related to their use (placement on the body, calibration), IMUs suffer from a lack of robustness and precision of measurement. The main problem with these sensors is the drift of the gyroscope (one of the components of the IMUs), which causes a measurement error that is becoming more and more important over time. To correct this error, it is possible to use the magnetometer. However, the latter is disturbed by the presence of iron in the measurement environment, which renders it inoperative for measurements in the industry.

Far be it from us to denigrate this technology, on the contrary, we use it to specifically measure wrist movements, as rarely visible by the camera (objects, tools). The error in measuring the sensors trade is a major problem to get a valid data because it will help you must recalibrate them every 3-4 minutes during the measurement, which is unacceptable for us.

But all is not lost because we have developed our own sensors resistant to measurement drift problems. This new innovation results will be presented in more detail in the next article, then stay tuned 😉

Pierre Plantard


Literary entry: Pierre Plantard contributes to the 1st edition of the book "DHM and Posturography"

With his expertise in the use of depth cameras in postural analysis, Pierre Plantard contributed to the 1st edition of the scientific book "DHM and Posturography". This book, published on August 23, explores the body of knowledge and the state of the art of digital human modeling, as well as its applications in ergonomics and posturography. The book provides a first glimpse into the human simulation tool industry, with detailed chapters describing posture elements, postural interactions and fields of application.

Our founder looked at the issue of integrating a technology such as depth cameras for industrial application into the field of postural analysis for ergonomics. It draws on both these years of research and field experience with industrial partners.

Link to the detailed description of the book

Occupational risk pricing AT/MP

Each year the contribution rates are determined by the CRAMIF or CARSAT services and defined by a ministerial order. Objective to enable companies to contribute (employer contribution) and protect employees.

Cotisation.en

This contribution rate varies depending on the size of the (national workforce), the business sector (risks incurred by the employees), the loss of the institution concerned. The rate is given every year to businesses.

Each activity has a “risk code” determined by based on the main activity for the largest number of employees in the the company. 2 digits 2 letters (ex 55 3BC), 208 nomenclature risks in 9 sectors. This code should not be confused with the APE code (rather economic indicator). the risk code determines the risk incurred by the Employees.

There are 3 types of pricing:

  • Collective pricing for companies less than 20 employees. The rate is defined collectively according to the of sectoral elements
  • Individual pricing for companies 250 employees. The rate is calculated from the elements of the the establishment
  • Mixed pricing for companies between 21 and 249 employees

The purpose of the calculation method is to rely on the the company’s disaster. In this way there is now, since 2018, a a real financial impact on the contribution rate in a sense as in the the other to “reward” the efforts and actions of prevention.

Source: Conference CRAMIF Preventica 2019 Ff

Risk prevention and digital transformation

The time we hear about big data, sensors, reality Virtual… technologies infusing all sectors of activity. The prevention sector is not spared. And applications and uses are for many yet to invent. Some concrete examples of this the appropriation of new technologies through the prevention of risks at work *.

Sensors

The installation of sensors in a parking lot under terrain for example allows you to measure in time the peaks of pollution and to trigger the real-time breakings. Objective: to ensure user comfort (especially sound) and save energy. These same sensors in the the tertiary sector makes it possible to objectify the feelings of atmosphere. Visibility Live from the atmosphere to have targeted actions on the offices by example.

RFID chips and mobility

Better manage equipment, non-conformities and respond to the security obligations of people and property through RFID chips is now possible. The chips allow to better share the information, identify, tag, track and add information about the facilities and make them readily accessible to all stakeholders. Coupled with artificial intelligence, fleas can be used to retranspose models and to go more and more towards predictive maintenance in rebuilding the scenarios. Also via smartphones it is possible to to bring an interesting dimension of mobility.

Drone and AI

Making inaccessible accessible is the Mission of Drones. They offer the possibility to work on images, allow to inspect parks for facilities that are not readily accessible. In Association artificial intelligence it is possible to raise several sites and to build models to see the evolution of the structure on the a certain period of time and bring alerts when you think there is a danger for man.

Training and reality Virtual

The human aspect is important in prevention. The appearance training to anchor knowledge and good practices is Essential. It is no longer enough to bring knowledge. With reality virtual it is possible to simulate situations, site visits,… And ensure the safe learning of gestures.

Source: Conference Preventica 2019 APAVE

Which trades can be affected by KIMEA in your company?

For several months we have been talking about our solution software and its technological aspect. Its strengths for ergonomists. But did you know that ergonomists do not have the exclusive use of KIMEA. The tool can also help other trades. We're explaining this to you.

Are you a prevention technician?

During training at the future workstation, KIMEA will be interesting to learn the right gesture. It will bring a playful point of view for sometimes long courses. The impact of the images is stronger and guarantees better memorisation on the part of the employee.

Are you a work doctor?

The overall view of a post and the scores by articulation will allow you to better target the workstations on which an operator can resume his activity in the event of a contraindication or in case of return to work.

Are you a method engineer? 

KIMEA allows you to have real-time data relative to the prescribed. This will allow you to easily identify if there is a gap between the prescribed range times and the actual time. In addition, when you return each task for each workstation, you will be able to create a detailed activity diagram (time, MSDS risks, solicited joints,…)

Are you a production manager?

The tool allows you to do a mapping of workstations and to have a global vision. You will be able to make rotating loops of your collaborators who do not solicit the same joints. And compared to competing tools, we guarantee you a time saver. Indeed, without sensors or combinations, there is no need to stop the production line several minutes to start analyzing. Finally you can have a global view of your site from a physical and biomechanical point of view.