Five seconds - is it a lot or a little? To drink hot coffee is not enough, to attach a card and go to work is a lot. But sometimes, even because of such a delay, queues form at the checkpoints, especially in the mornings. Now let's fulfill the requirements for the prevention of COVID-19 and start taking the temperature of all incoming people? The passage time will increase by 3-4 times, because of this a crowd will appear, and instead of fighting the virus, we will get ideal conditions for its spread.
To prevent this from happening, you need to either organize people in a queue, or automate this process. In the second option, it is necessary to read the temperature of a large number of people at once, without loading them with additional actions. This can be done by adding a video surveillance system and perform several actions at once: identify faces, measure temperature and determine the presence of a mask. We talked about how such systems work at our conference "βAnd weβll tell you more under the cut.
Where are thermal imaging systems used?
A thermal imager is an optical-electronic device that "sees" in the infrared spectrum. Yes, this is the same thing from action movies about dashing special forces and films about the Predator, which beautifully paints an ordinary image in red and blue tones. In practice, there is nothing unusual in it and they are used quite widely: thermal imagers determine the position and shape of heat-radiating objects and measure their temperature.
In industry, thermal imagers have long been used to monitor temperatures in production lines, industrial equipment, or pipelines. Often, thermal imagers can be seen along the perimeter of serious objects: thermal imaging systems βseeβ the heat that a person radiates. With their help, security systems detect unauthorized entry to the object even in absolute darkness.
Due to COVID-19, thermal cameras are increasingly being integrated with biometric identification systems for access control. For example, integrated intoΒ» (Rostelecom's integrated solution, which is developed and manufactured in Russia), thermal imaging devices can measure the temperature of people, track movement and highlight individuals with elevated temperatures.
There are no mandatory standards for the use of thermal imaging systems in Russia, but there is a general , according to which it is necessary to control the temperature of all visitors and employees. And thermal imaging systems do this almost instantly, without requiring additional actions from employees and visitors.
How non-contact in-line temperature measurement systems work
The basis of the system is a thermal imaging complex of thermal imaging and conventional cameras, which are packaged in a common housing. If you are walking down a corridor and a plump two-eyed camera is staring into your face, this is a thermal imager. The Chinese pranksters sometimes make them in a white case and add little "ears" to make them look more like pandas.
Simple optics are needed for integration with BioSKUD and the operation of face recognition algorithms - for identifying and checking the presence of personal protective equipment (masks) for incoming people. Additionally, through a conventional camera, you can control the distance between people or between people and equipment. In the software, video information about the measurement results is displayed in the form familiar to the operator.
In order for the thermal imager to react only to the temperature of people, it already has a face detection algorithm. The equipment reads the temperature from the thermal matrix at the right points - in this case, in the forehead area. Without this βfilterβ, the thermal imager would respond to cups of hot coffee, incandescent bulbs, etc. Additional functions include monitoring the presence of protective equipment and keeping a distance.
Usually, at the entrance to the premises, thermal imaging systems are integrated with access control and management systems. The complex is connected to the server, which processes the incoming data with video analytics algorithms and transfers them to the operator's automated workstation (AWS).
If a thermal imaging camera detects an elevated temperature, then a regular camera takes a photo of the visitor and sends it to the control system for identification with the base of employees or visitors.
Calibration of thermal imaging systems: from reference samples to machine learning
To set up and operate in-line non-contact temperature measurement, it is usually used black body (blackbody), which at any temperature absorbs electromagnetic radiation in all ranges. It is installed in the field of view of the thermal imaging camera and is used to calibrate the thermal imager. A reference temperature of 32β40 Β°C (depending on the manufacturer) is maintained in the black body, with which the equipment βverifiesβ every time when measuring the temperature of other objects.
It is inconvenient to use such a system. So, for the correct operation of the thermal imager, the black body must warm up to the desired temperature for 10β15 minutes. At one facility, the thermal imaging complex was turned off for the night, and in the morning the blackbody did not have time to warm up properly. As a result, all those entering at the beginning of the shift had an elevated temperature. Later we figured it out, now the thermal imaging complex is not turned off at night.
Now we are developing an experimental technology that allows us to do without blackbody. It turned out that our skin is close to a completely black body in its characteristics, and a person's face can be used as a reference. We know that most people have a body temperature of 36,6Β°C. If, for example, you track people with the same temperature for 10 minutes and take this temperature as 36,6 Β° C, then you can calibrate the thermal imager by their faces. This technology, implemented with the help of artificial intelligence, shows good results - no worse than those of thermal imaging systems with blackbody.
Where the blackbody is still used, artificial intelligence is helping to calibrate thermal imagers. The fact is that most thermal imaging systems involve manual installation of a thermal imager and its adjustment to the blackbody. But then, when conditions change, the calibration has to be done again, otherwise thermal imagers start showing temperature with deviations or react to visitors with normal temperature. Manual calibration is such a joy, so we developed an AI-based module that is responsible for detecting blackbody and adjusts everything itself.
Is it possible to disguise yourself from algorithms
Artificial intelligence and machine learning are often used in contactless biometrics. AI is responsible for detecting faces in a stream to measure temperature, ignoring foreign objects (a hot cup of coffee or tea, lighting elements, electronics). Well, training algorithms for face recognition in masks is a must have for any system since 2018, even before the coronavirus: in the Middle East, people cover a significant part of their faces for religious reasons, and in many Asian countries, masks have long been used to protect against the flu or urban smog. Recognizing a half-hidden face is more difficult, but algorithms are also improving: today, neural networks detect masked faces with the same probability as a year ago without masks.
It would seem that masks and other personal protective equipment should have become a problem in identification. But in practice, neither the presence of a mask, nor a change in the hairstyle or shape of the glasses affect the recognition accuracy. Algorithms for face detection use points from the eye-ear-nose region that remain open.
The only "failure" situation from our practice is associated with a change in appearance with the help of plastic surgery. An employee after plastic surgery was unable to pass through the tourniquets: biometric processors could not identify her. I had to update the photo in order for face geometry access to work again.
Capabilities of thermal imaging systems
Measurement accuracy and its speed depend on the resolution of the thermal imager matrix and its other characteristics. But software is behind any matrix: the video analytics algorithm is responsible for determining objects in the frame, for their identification and filtering.
For example, the algorithm of one of the complexes measures the temperature of 20 people at the same time. The throughput of the complex is up to 400 people per minute, which is enough for use at large industrial enterprises, at airports and train stations. At the same time, thermal imagers record the temperature at a distance of up to 9 meters with an accuracy of plus or minus 0,3 Β°C.
There are better complexes. However, they can also effectively cope with their tasks. One of the solutions is the integration of a thermal imager into the frame of a metal detector. Such a set of equipment is suitable for checkpoints with a small flow of visitors - up to 40 people per minute. Such equipment detects people's faces and measures temperature with an accuracy of 0,5 Β°C at a distance of up to 1 meter.
Problems when working with thermal imagers
Non-contact measurement of the temperature of people in a stream cannot yet be called perfect. For example, if in cold weather a person was outside for a long time, at the entrance the thermal imager will show the temperature 1β2 Β°C lower than the real one. Because of this, the system may allow people with elevated temperatures to enter the facility. This can be solved in different ways, for example:
- a) create a thermal corridor so that before measuring the temperature, people adapt and move away from the frost;
- b) on frosty days, add 1-2 Β° C to the temperature of all incoming guests - however, those who arrived by car will fall under suspicion.
Another problem is the price tag of accurate thermal imaging systems. This is due to the high cost of production of a thermal imaging matrix, which requires precise calibration, germanium optics, etc.
Source: habr.com