Mospolitech: Vision System

The main articles are:

• Computer vision (machine vision)
• Video analytics (terms, applications, technologies)

2023: System Development

Evgeny Pikalov, an employee of the Department of Automation and Control at the Moscow Polytechnic, developed a vision system for determining the distance to an object based on the triangulation method. The project is being implemented at the expense of a grant named after V. Fortov under the Priority 2030 program. The university announced this on March 9, 2023.

To study the binocular vision system, the scientist used two cameras and a computer to process information. He investigated the dependencies between the internal parameters of the system and the accuracy of calculating the distance to the tracked object.

I was able to confirm the assumption that the entered calibration coefficient can be calculated through automated calibration, - Yevgeny Pikalov described his result. - In my work, I turned to the method of binocular vision based on triangulation. The methods used for March 2023 have a number of disadvantages. The binocular system, in my opinion, wins, which I managed to prove by achieving higher accuracy.

With the help of technical vision, automated and automatic systems such as cars, quadcopters, warehouse loaders, production manipulators and others are "humanized." This is in demand in the construction of pilot cars, in production, on roads.

The study was conducted on long-purchased low-cost cameras. They usually give low accuracy. It turned out that even on outdated equipment, accuracy can be increased. This is a scientist and demonstrated on a model assembled with his own hands. In the future, it is planned to investigate the system in relation to the production process.

It is interesting to investigate something spherical and in a vacuum, but it is more important to understand what this system may be suitable for and, taking into account the relevant requirements, adjust the study. I would like it to become a complete development, which can be used to solve real problems, - summarizes Evgeny Pikalov.