Let's take a closer look at the capabilities of an IP camera for reading numbers.

It can be used for the following purposes:

• automated opening of the barrier at the entrance to the controlled area;
• automated issuance of fines when the driver violates the rules in the coverage area of ​​the camera with recognition car numbers.
• to automatically calculate the cost of parking based on vehicle data.
• immediate notification of detection the desired car by comparing its number with the database.

All these analytical processes are performed by internal software in automatic mode, or with settings and specified functions from the user, through the software installed on the server. Starting to work with an IP camera for license plate recognition, it is recommended that you read the instructions for installing, configuring and operating the device. A network license plate camera can have a different form factor and type of installation. The selection should be based on current requirements and conditions.

We offer to buy IP cameras for license plate recognition, at a price of 3000 rubles in our online store. All the necessary information about the device is available on the site.

Features of IP camera for license plate recognition

Before you buy an IP camera with license plate recognition, check out its technical specifications.

List of technical characteristics:

• Power supply parameters.
• Type of software, ease of management.
• IP camera protection class.
• Viewing angle.
• Permission.
• Installation and connection method.
• The speed of information processing, search for matches.
• The speed of shooting, recording.
• Temperature regime camera work.
• Maximum permissible air humidity
• Rating of the manufacturer's brand on the market of control systems and video surveillance, user reviews.
• Dimensions, weight of the device.
• Complete set, availability of fasteners necessary for installation, operating instructions.

The cameras presented in this section have been checked by our specialists for compatibility with the software Macroscop "License plate recognition". In combination with this software, our cameras will provide you with constant control over the protected area, help you find the right car, and automate a number of processes.

Having chosen a device that meets all the requirements, you can quickly place an order on the website. We will deliver a video camera with license plate recognition to the desired object in Moscow as soon as possible.

It's time to tell in detail how our implementation of the license plate recognition algorithm works: what turned out to be a good solution, what worked very badly. And just report to Habr-users - after all, you, using the Android application Recognitor, helped us to collect a decent-sized database of snapshots of rooms taken with a completely open mind, without explaining how to shoot, and how not. And the base of images is the most important thing in the development of recognition algorithms!

What happened with the Android app Recognitor

It was very nice that Habr's users started downloading the application, trying it and sending us numbers.

Program downloads and evaluations

Since the application was uploaded to the server, 3,800 pictures of numbers from the mobile application have been received.
And we were even more pleased with the link http://212.116.121.70:10000/uploadimage - in 2 days we were sent about 8 thousand full-size photographs of car numbers (mainly Vologda)! The server was almost down.

Now we have a base of 12,000 photographs in our hands - a gigantic work of debugging algorithms lies ahead. All the fun is just beginning!

Let me remind you that a number was pre-allocated in the Android application. In this article, I will not dwell on this stage in detail. In our case, a cascade Haar detector. This detector does not always work if the number in the frame is strongly rotated. I will leave the analysis of how the trained cascade detector works when it does not work for the next articles. It's really very interesting. It seems that this is a black box - the detector has been trained and nothing else can be done. In fact, this is not the case.

Still, a cascade detector is a good option in the case of limited computing resources. If the license plate is dirty or the frame is poorly visible, then Haar also performs well in relation to other methods.

License plate recognition

Here is a story about text recognition in pictures of this kind:

General approaches to recognition were described in the first article.

Initially, we set ourselves the task of recognizing dirty, partially erased and heavily distorted by perspective numbers.
Firstly, it is interesting, and secondly, it seemed that then the clean ones would work in general in 100% of cases. This is usually the case, of course. But it didn't work out. It turned out that if for dirty numbers the probability of success was 88%, then for clean numbers, for example, 90%. Although in reality, the probability of recognition from a photo on a mobile application to a successful answer, of course, turned out to be even worse than the indicated figure. Slightly less than 50% of incoming images (so that people do not try to take pictures). Those. on average, the license plate had to be photographed twice in order to recognize it successfully. Although, in many ways, such a low percentage is due to the fact that many tried to remove numbers from the monitor screen, and not in a real situation.

The whole algorithm was built for dirty numbers. But it turned out that now in the summer in Moscow, 9 out of 10 rooms are perfectly clean. So it is better to change the strategy and make two separate algorithms. If we managed to quickly and reliably recognize a clean number, then we will send this result to the user, and if it was not possible, then we spend a little more processor time and run the second algorithm for dirty numbers.

A simple number plate recognition algorithm that would be worth implementing right away

How do you recognize a nice and clean room? It's not difficult at all.

We present the following requirements for such an algorithm:

1) some resistance to turns (± 10 degrees)
2) resistance to slight changes in scale (20%)
3) cutting off any boundaries of the number by the frame boundary or simply poorly expressed boundaries should not destroy everything (this is fundamentally important, since in the case of dirty numbers you have to rely on the number boundary; if the number is clean, then nothing better than numbers / letters characterizes room).

So, in clean and well-readable numbers, all numbers and letters are separable from each other, which means that you can binarize the image and use morphological methods to either select related areas, or use the well-known outline selection functions.

Binarize the frame

Here it is still worth going through the middle pass filter and normalizing the image.


The image shows an initially low-contrast frame for clarity.

Then binarize using a fixed threshold (you can fix the threshold, since the image has been normalized).

Frame rotation hypotheses

Let's assume several possible angles of image rotation. For example, +10, 0, -10 degrees:

In the future, the method will have a slight resistance to the angle of rotation of numbers and letters, therefore such a sufficiently large step in the angle is chosen - 10 degrees.
In the future, we will work with each frame independently. What rotation hypothesis will give best result, she will win.

And then collect all related areas. The standard function was used here findContours from OpenCV. If the associated area (outline) has a height in pixels from H1 to H2 and the width and height are related by the ratio from K1 to K2, then we leave it in the frame and note that there may be a sign in this area. Almost certainly at this stage, only numbers and letters will remain, the rest of the debris will go away from the frame. Take the bounding rectangles, bring them to the same scale and then work with each letter / number separately.

Here are the path bounding boxes that met our requirements:

Letters / numbers

The image quality is good, all letters and numbers are perfectly separable, otherwise we would not have reached this step.
Scale all signs to the same size, for example, 20x30 pixels. Here they are:

By the way, OpenCV will turn the binarized image into a gradient image when Resize (when converting to a size of 20x30), due to interpolation. We'll have to repeat binarization.

And now the easiest way to compare with known sign images is to use XOR (Normalized Hamming Distance). For example like this:

Distance = 1.0 - | Sample XOR Image | / | Sample |

If the distance is greater than the threshold, then we consider that we have found a sign, less - we throw it out.

Letter-number-number-number-letter-letter

Yes, we are looking for Russian car signs in this format. Here you need to take into account that the number 0 and the letter "o" are generally indistinguishable from each other, the number 8 and the letter "v". Let's line up all the signs from left to right and take 6 signs each.
The criterion of times is letter-number-number-number-letter-letter (do not forget about 0 / o, 8 / v)
Criterion two - deviation of the lower boundary of 6 characters from the line

Hypothesis Total Points - the sum of the Hamming distances of all 6 digits. The bigger, the better.

So, if the total points are less than the threshold, then we consider that we have found 6 digits of the number (without the region). If there is more than a threshold, then we go to an algorithm that is resistant to dirty numbers.

It is also worth considering separately the letters "H" and "M". To do this, you need to create a separate classifier, for example, based on the gradient histogram.

Region

The next two or three characters above the line drawn along the bottom of the 6 characters already found are the region. If the third digit exists, and its similarity is more than the threshold, then the region consists of three digits. Otherwise, of the two.

However, region recognition often does not go as smoothly as we would like. The numbers in the regions are smaller, they may not be successfully divided. Therefore, it is better to recognize the region in a way that is more resistant to dirt / noise / overlap, described below.

Some details of the description of the algorithm are not disclosed in great detail. Partly due to the fact that now only a mock-up of this algorithm has been made and it has yet to be tested and debugged on those thousands of images. If the number is good and clean, then you need to recognize the number in tens of milliseconds or answer “failed” and go to a more serious algorithm.

Dirty Number Resistant Algorithm

It is clear that the algorithm described above does not work at all if the signs on the license plate stick together due to poor image quality (dirt, poor resolution, unsuccessful shadow or shooting angle).

Here are examples of numbers when the first algorithm failed to do anything:

But you will have to rely on the boundaries of the license plate, and then, within a strictly defined area, look for signs with a precisely known orientation and scale. And most importantly - no binarization!

We are looking for the lower border of the number

The simplest and most reliable step in this algorithm. We iterate over several hypotheses by the angle of rotation and build for each hypothesis by rotation a histogram of pixel brightness along the horizontal lines for the lower half of the image:

Let's choose the maximum of the gradient and so determine the angle of inclination and at what level cut off the number from the bottom. Let's not forget to improve the contrast and get this image:

In general, it is worth using not only the luminance histogram, but also the variance histogram, the gradient histogram, to increase the reliability of the number clipping.

We are looking for the upper limit of the number

Here it is no longer so obvious, it turned out that if the rear license plate is removed from the hands, then the upper border can be strongly curved and partially cover the signs or in the shade, as in this case:


There is no sharp transition of brightness in the upper part of the number, and the maximum gradient will cut the number in the middle altogether.

We got out of the situation not very trivially: we trained a cascade Haar detector for each digit and each letter, found all the signs in the image, so we determined the top line where to cut:

It would seem that it is worth stopping here - we have already found numbers and letters! But in reality, of course, the Haar detector can be wrong, and we have 7-8 signs here. A good example of the number 4. If the upper border of the number merges with the number 4, then it is not at all difficult to see the number 7. Which, incidentally, happened in this example. But on the other hand, despite the error in detection, the upper border of the found rectangles really coincides with the upper border of the license plate.

Find the side borders of the number

Nothing tricky either - absolutely the same as the bottom one. The only difference is that often the brightness of the gradient of the first or last character in the number can exceed the brightness of the gradient of the vertical border of the number, so not the maximum is selected, but the first gradient exceeding the threshold. Similarly, with the lower boundary, it is necessary to sort out several hypotheses for the slope, since due to the perspective, the perpendicularity of the vertical and horizontal boundaries is not at all guaranteed.

So here's a nicely cropped number:

Yes! especially nice to insert a frame with a disgusting number, which was successfully recognized.

The only sad thing is that by this stage from 5% to 15% of the numbers may be cut off incorrectly. For example, like this:

(by the way, it was someone who sent us a yellow taxi number, as far as I understood - the format is not regular)

All this was necessary so that all this was done only to optimize the calculations, since it is very computationally expensive to sort out all possible positions, scales and slopes of the signs when searching for them.

Split string into characters

Unfortunately, due to the perspective and not standard width all are familiar, you have to somehow select the characters in the already truncated number. Here again the histogram for brightness will help out, but already along the X axis:

The only thing that is worth investigating in the future are two hypotheses: the symbols start immediately or one maximum of the histogram should be skipped. This is due to the fact that on some license plates the screw hole or the screw head of the license plate may differ as a separate sign, or may be completely invisible.

Character recognition

The image is still not binarized, we will use all the information that we have.

Here are printable characters, so weighted covariance is suitable for comparing images with an example:

Samples for comparison and weights with covariance:

Of course, you can't just compare the area highlighted with the horizontal histogram with the samples. We have to make several hypotheses in terms of displacement and scale.
Number of hypotheses by position along the X axis = 4
Number of hypotheses by Y-axis position = 4
Number of hypotheses by scale = 3

Thus, for each area, when comparing with one sign, it is necessary to calculate 4x4x3 covariances.

The first step is to find 3 large numbers. This is 3 x 10 x 4 x 4 x 3 = 1,440 comparisons.

Then one letter on the left and two more on the right. There are 12 letters for comparison. Then the number of comparisons is 3x12x4x4x3 = 1728

When we have 6 characters, then everything to the right of them is a region.

The region may have 2 digits or 3 digits - this must be taken into account. It makes no sense to split the region using the histogram method because the image quality may be too low. Therefore, we simply find the numbers one by one from left to right. Starting from the upper left corner, several hypotheses are needed on the X-axis, Y-axis and scale. Finding the best match. We move to the right by a given amount, we search again. We will look for the third character to the left of the first and to the right of the second, if the similarity measure of the third character is greater than the threshold, then we are lucky - the region number consists of three digits.

conclusions

The practice of using the algorithm (the second one described in the article) has once again confirmed the truism in solving recognition problems: you need a truly presentational base when creating algorithms. We were targeting dirty and shabby rooms as the test base was filmed in winter. Indeed, it was often possible to recognize rather bad numbers, but there were almost no clean numbers in the training sample.

The other side of the coin also came to light: there is little that annoys the user as much as the situation when automatic system does not solve a completely primitive problem. "Well, what can not be read here ?!" And the fact that the automatic system was unable to recognize dirty or worn numbers is expected.

Frankly speaking, this is our first experience in developing a recognition system for a mass consumer. And it is worth learning to think about such "little things" as users. Now we are joined by a specialist who has developed a similar "Recognitor" program for iOs. In the UI, the user has the opportunity to see what is being sent to the server, to select which of the numbers allocated by Haar is needed, it is possible to select the necessary area in an already "frozen" frame. And it's already more convenient to use it. Automatic recognition becomes not a stupid function, without which nothing can be done, but just an assistant.

Thinking over a system in which automatic image recognition would be harmonious and convenient for the user turned out to be no easier task than creating these recognition algorithms.

And, of course, I hope this article will be helpful.

1.1 Cameras

DS-2CD4A25FWD-IZ (H) (S) Lightfighter bullet and

DS-2CD4A26FWD-IZ (H) (S) Darkfighter bullet

Outdoor bullet camera with IR illumination

1. Works in very low light conditions,
2. excellent work of compensation of oncoming light,
3. cylindrical, weatherproof, robust housing,
4. license plate recognition,
5. b / w filter list,
6. alarm output

1. Darkfighter Ultra-low light technology High definition 1920x1080
2. Up to 60fps @ Full HD1080p 120dB WDR
3. 2.8 ~ 12mm Motorized VF Intelligent Auto Focus Lens
4. H.264 smart codec + compact compression IR illumination 50m.
5. IP67 protection
6. Power supply + -12V DC and PoE
7. Built-in storage, support up to 128GB
8. ANPR, B / W List Filtering support

Options:

Built-in heater (-H)

Audio / Alarm I / O (-S)

Cameras suitable for license plate recognition are initially supplied with firmware for counting passers-by,

therefore, at the request of the customer, they are reflashed for this function.

The flashing does not completely remove the counting function and allows you to return to it if desired by selecting the SMART Event, as shown in the figure below.

1.2 Solution

Solutions Hikvision's license plate recognition provided by the camera itself can be divided into:

1). Classic license plate recognition and issuing a list of recognized numbers directly from the camera

1. Actions if the number matches the list recorded in the camera (admission to the territory, turning on the siren, sending a message)

When a number appears from the list, the chamber's dry contact is closed, which is a signal for the barrier control unit.

2. Requirements for the camera and installation site

2.1. The license plate must be legible and well lit.

2.2. The license plate must be at least 150 pixels wide.

2.3. Allowable tilt - no more than 5 ° (clockwise and counterclockwise).

2.4. Vertical angle - no more than 30 °.

The original formula is � = ℎ ∗ √3.

2.5. Horizontal angle - no more than 30 °.

2.6. If it is necessary to recognize license plates from two lanes, as a rule, it is recommended to place the camera on a crossbar.

2.7. It is necessary to choose the correct distance from the camera to the recognition site

2.8. When recognizing license plates at night, an IR illumination is required.

2.9. The shutter speed should be fast enough to reduce headlamps at night. As a rule, we are talking about 1⁄1000.

2.10. The depth of focus is a very important parameter. If you are using a camera with a CS lens mount, use a fixed lens. Fixed lenses are better for recognition because of the greater depth of focus.

2.11. When choosing a mounting location, remember that direct sunlight can distort the picture.

2.12. When installing the camera on the side of the road, check how the support responds to the passage of heavy vehicles or convoys. If the support has significant vibrations, this will affect the efficiency of the system.

2.14. In rare cases, a situation of false detections may arise.
To minimize this, you need the following:

1. select the recognition area correctly.
2. try changing the angle of view or the location of the camera.
3. adjust the settings for the minimum and maximum license plate size in the settings.

3. Vehicle detection

An intelligent IP camera detects a car by identifying and recognizing a license plate, issuing the following data to the registrar, iVMS-5200 or another consumer:

1. Travel time (hours and minutes)
2. Direction of travel ("entry" and "exit" when choosing a travel zone)
3. License plate (letters and numbers)
4. Country of registration (name)
5. Screenshot with number (small picture)
6. Full screen screenshot
7. Video of the moment of determination (+/- 1-5s)
8. Auto-recognition of black / white lists (issuing the corresponding alarm)
9. Alarm output relay actuation (on the camera itself, set up separately in the recorder)

The information received from the camera is managed by the corresponding consumers:

You can configure the transfer of information and the actual recognition of license plates on the camera on the following consumers:

a) Configuring recognition on localNVR

If NVR is connected to iVMS-4200, then DVR and camera can be configured from it:

b) Recognition viVMS-4200

And even in iVMS-4200, you can perform all the control of the recognition process, but independently without an NVR, it is just a shell that can only use the usual functions of video surveillance from these cameras.

c) Configuring recognition oniVMS-5200 P

IVMS-5200 Pro has advanced analytics that uses license plate recognition in different types activities of society and business.

Configuring recognition on camera

On the camera itself, through the web-inteface, you can configure it for any user, adjusting it already on it, but to connect the actuator, the setting is done only on the camera.

This is where we will be looking at the vehicle detection function to open the barrier.

4. Camera setup

4.1. To process a license plate recognition event, such as opening a barrier, first of all it is necessary to set up the "Alarm output", by closing the dry contact of which the mechanism will be triggered.

Without this, there will be no electrical reaction to a further adjustable recognition.

However, if the use of mechanization is not planned, then this is not necessary.

4.2. As a rule, it is not supposed to open the barrier for all visitors, but only for “our own”, or in extreme cases, not to let only certain ones. Therefore, it is necessary to enter ahead of time the "white" and "black" list of numbers, for which you need to get its form from the camera itself by pressing the "export" button.

I would like to draw your attention to the name of the font used in the document, which, of course, is not in your system, but it is it that is necessary for the camera to correctly perceive your presets:

Having filled in the file with the list of numbers, you need to select the filled cells of the header row, making sure that the font is named in Chinese, and then use the Excel button to copy the format by sample

Then you need to apply this format to all the cells you entered, highlighting them so that they are all written in a font with a Chinese name.

4.3. After importing the prepared Excel file, the camera will fill in the data of the "white" and "black" lists:

Note: Unfortunately, with lists while somewhat sad:

And now, only after all that has been done previously, you can proceed to setting up license plate recognition and turning on the trigger reaction to numbers from the "white" list

4.4. Set the number of recognition bands and adjust the zone, and then select the region.

Supported countries in the "EU and CIS" option:

Czech Republic, Germany, Spain, France, Italy, Netherlands, Poland, Slovakia, Belarus, Moldova, Ukraine, Russia, Belgium, Bulgaria, Denmark, Finland, Great Britain, Greece, Croatia, Hungary, Israel, Luxembourg, Macedonia, Norway, Portugal, Romania, Serbia, Azerbaijan, Georgia, Kazakhstan, Lithuania, Turkmenistan, Uzbekistan, Latvia, Estonia, Austria, Albania, Bosnia and Herzegovina, Republic of Ireland, Republic of Iceland, Vatican, Republic of Malta, Sweden, Switzerland, Cyprus, Turkey, Slovenia.

4.5. Select the "In / Out" mode.

4.6. Check and resave the schedule.

4.7. Turn off "All" by selecting "White List" and enable the alarm output to be triggered.

4.8. Turn on recognition and save the settings.

5. License plate recognition

1. The recognition process can be seen in a special setting tab.

1. However, the results of detection and recognition can only be seen in the archive of the registrar.
2. The camera will be able to write to its own memory card only constantly and by events:

Screenshots of license plate identification can also be sent to the FTP server by checking the box in the Communication method section of the Search configuration tab of the Traffic menu.

6. Conclusion

Dont be upset! On NVR, iVMS-4200 & 5200 all the above mentioned problems are not present! Everything works correctly there and has great functionality!

Technologies for software recognition of license plates and human faces are becoming more and more in demand. For example, automatic license plate recognition can be used as a component of an access control system, for organizing billing systems for paid parking, automating car admission, or for collecting statistical information (repeated visits to a mall or a car wash, for example). All this is within the power of modern intelligent software. What is needed to implement such a system? In principle, not so many - video cameras that meet certain requirements and the corresponding intelligent software module. For example, software or more budgetary

In this article, we will tell you how to choose the right digital video camera capable of generating high-quality video images suitable for the tasks of software license plate recognition.

Permission

Until a few years ago, the size of a license plate on the screen was measured in% of the frame width. All cameras were analog and their resolution was constant. Now, when matrices can have a resolution from 0.5 to 12MP, relative values ​​are not applied and the required license plate width is measured in pixels.

As a rule, the specification for license plate recognition software specifies the requirements for the width of the license plate on the screen, sufficient for confident recognition. So, for example, the AutoTrassir software module requires a width of 120 pixels, and NumberOK - 80 pixels. Differences in the requirements are explained both by the nuances of the recognition algorithms and by the acceptable level of reliability adopted by the developer. From personal experience, it can be noted that AutoTrassir is more demanding and "capricious" in terms of the choice of equipment, lens, and the correct installation of the camera. But, being brought to mind, it shows consistently reliable results and depends little on weather conditions.

For greater reliability, we can recommend focusing on the value of the license plate width of 150 pixels. And if we remember that the width of the license plate in accordance with GOST is half a meter (520mm to be precise), then we come to the required resolution of 300 points per meter.

The linear resolution of pixels per meter depends on the viewing angle and resolution of the camera matrix. You can calculate it using the formula:

R lin- linear resolution, pixels per meter

R h- horizontal resolution of the camera (for example,R h =1080)

𝛼 - angle of view of the camera

L- distance from camera to object

You can also use our online calculator on the page of the product you are interested in, on the "What will I see" tab.

Below is (for example) several options for IP video surveillance cameras, indicating the maximum distance from which license plate recognition is possible (license plate width 150 pixels). Please note that for cameras with a varifocal lens, the maximum focal length was used in the calculation.

	Focal length	Horizontal Resolution	Max. distance, m	Max. width of view, m
		1920 pixels
		1280 ppi
		2688 ppi
		2048 ppi
		2048 ppi

It is important to understand that higher resolution cameras can monitor wider areas, so fewer areas are required per area. In this case, the linear resolution remains within the identification requirements. This fact makes it economically viable to use high definition cameras in many situations.

Light sensitivity and shutter speed

For confident recognition of car license plates, the camera must have good light sensitivity and the ability to manually set the shutter speed (shutter speed or just shutter speed). This requirement is extremely important when building systems for recognizing license plates of cars moving at high speed. For cars moving at speeds up to 30 km / h (and it is such projects that we, as a rule, implement for our customers: cottage settlements, residential complexes, parking lots of shopping centers, various closed areas) this requirement is less important, but it cannot be underestimated, because for achievement High Quality recognition camera must take at least ten frames with a readable number.
Therefore, for example, to recognize a license plate moving at a speed of 30 km / h at an angle of installation of the camera up to 10 degrees relative to the axis of motion, the shutter speed should be about 1/200 of a second. For many inexpensive cameras, such exposure even during the daytime in cloudy weather may be insufficient, and the picture will turn out to be dark and / or noisy. Therefore, it is worth paying close attention to the size of the matrix and its quality. Ideally, use a dedicated black and white CCD camera. However, their price is very high and the resolution is usually no more than 1 megapixel, which imposes serious restrictions on their applicability.
In general, one should not chase high resolution unless there are objective reasons for that. Relatively inexpensive ultra-high-resolution cameras (4MP, 5MP and higher) are built on matrices of 1/3, 1 / 2.8 and, less often, 1 / 2.5 inches. Cameras with 1.3 and 2MP resolution have the same matrix size. As a result, the size of each photosensitive element in a 1.3MP camera is noticeably larger than in a 5MP camera, and than bigger size- the more light each photosensitive element can collect. That is why the IP cameras recommended by us for number recognition tasks rarely have a resolution of more than 2MP.

Wide dynamic range (WDR), backlight compensation

The dynamic range of a camera determines the ratio between the maximum and minimum light intensity that its sensor can normally capture. In other words, it is the ability of the camera to transmit both brightly lit and dark areas of the image at the same time without distortion and loss. This parameter is very important for automatic license plate recognition, because helps to fight backlight from the camera headlights. However, even the most advanced 140dB WDR cameras are not always able to cope with high contrast lighting. In this case, additional illumination of visible light or operating in the infrared range is installed, illuminating the area in which the license plate is recognized.

Depth of field

Depth of field, or, completely, depth of field of the imaged space (DOF) is the range of distances in which objects are perceived as sharp.

This parameter is determined by focal length, aperture and distance to the subject. The deeper the depth of field, the larger the focus area and the more more possibilities"Catch" a sufficient number of clear shots of a moving car.

Perhaps, the lens aperture has the greatest influence on the depth of field. The smaller the aperture, the greater the depth of field, the larger, the less depth of field. All the cameras we recommend for license plate recognition are able to adapt to changing lighting conditions by automatically changing the aperture. It is recommended to adjust the focus of such cameras at the maximum open aperture, when the depth of field is minimal.

The greater the distance from the camera to the object, the greater the depth of field, so do not try to place the camera as close to the recognition zone as possible. On the other hand, the longer the focal length, the shallower the depth of field. In our practice, the optimal distance from the camera to the US is within the range of 6 to 10 meters. Although recognition is not impossible from a distance of 100 meters.

Distortion

Many lenses distort the image slightly. The most common is the so-called "barrel" distortion of the picture. This is due to the magnification, which is greater in the center and less at the edges, which causes the object to resize. So, if the same object falls into the center of the image and on its edge, its dimensions at the edge will seem smaller. This can affect the ability to identify.

The shorter the focal length, the more noticeable the distortion can be. Therefore, it is undesirable to use cameras with wide-angle lenses (less than 4mm) for identification.

Noise and color rendering

The less noise and the more accurate the color rendition, the better for identification. Therefore, it is recommended to pay attention to such parameters as the minimum illumination of the camera, as well as the presence of noise reduction functions.
Noise cancellation is especially important in low light conditions, when the camera sensors are "noisy", which makes identification difficult. It should be understood that in many cases, noise reduction and other electronic "gadgets" cannot cope, and you need to provide a sufficient level of lighting at the facility.

Compress video

Modern IP cameras transmit a compressed video signal, and if there is no movement in the frame or it is minimal, the traffic will be small. If the traffic in the frame is intense, the traffic will grow. Therefore, if a constant bit rate is set in the camera settings, the picture will be suitable for identification in the absence of movement, but unsuitable - with heavy movement in the frame.
For identification, it is recommended to set the variable bitrate with the highest quality level. In this case, the desired image quality will be provided.

Matrix: 1 / 2.8 "Progressive Scan CMOS Hardware WDR 140dB Lens: 2.8-12mm Features: the camera is internal, for outdoor installation you need a thermal casing. Lens not included and sold separately
Max. Resolution: 1.3MP, 1280 x 960 pixels Hardware WDR Lens: 2.8-12mm
Outdoor 2 MP Network Camera AXIS P1365-E with WDR and Lightfinder Matrix: 1 / 2.8 "Progressive Scan CMOS Max. Resolution: 2MP, 1920 x 1080 pixels Hardware WDR Lightfinder technology Lens: 2.8-8mm @ F1.3 Features: High sensitivity, autofocus
Dahua IPC-HF8301E Utlra WDR 120dB, Ultra 3DNR Matrix: 1/3 "Progressive Scan CMOS Max. Resolution: 3MP, 2048x1536 pixels Hardware WDR Lens: 2.8-12mm Features: the camera is internal, for outdoor installation you need a thermal casing. Lens not included and sold separately
Matrix: 1/3 "Progressive Scan CMOS Max. resolution: 1.3MP, 1280x960 pixels Lens: 2.8 - 8mm (F1.2) Features: High sensitivity, autofocus

There are many systems for automating the entry of cars into the territory of a protected facility. Starting from a banal guard in a booth with a button and ending with an electronic pass or a radio key fob.

The electronic license plate recognition system stands alone in this list and until recently was not very popular.

There are several reasons for this.

First, the high cost of equipment and the complexity of the setup. Secondly, the active rejection of innovation, including acts of blatant sabotage, by the guards themselves, whose work is now tightly controlled, excluding the possibility of additional earnings.

However, there are significant advantages that the license plate recognition system provides:

• a significant increase in the level of safety and control of road transport at the facility;
• the possibility for third parties to enter the protected area using fake or stolen magnetic passes or electronic key fobs is excluded. (a car can also be stolen, but it is much more difficult);
• automatic reporting of vehicles with the ability to generate multiple reports;
• remote access capabilities allow the management of the organization to control the work of employees;
• the license plate recognition system can be easily integrated into the general access control system of the organization.

The possibility to enter the territory of the guarded object by gluing the numbers printed on the printer to the car number is completely excluded. Almost all automatic license plate recognition systems control the light reflectance that paper does not have. The pasted number will simply not be read.

The scope of automated license plate recognition systems is quite diverse. First of all, license plate recognition will be useful at service stations, gas stations, car washes, warehouses, enterprises, parking lots.

The functions that such an automatic license plate recognition system can perform are quite diverse:

• control of entry and exit to the controlled area;
• restriction of leaving the territory of the enterprise, for example, a bus station, a client who has not made a payment;
• control over the loading of the service area.

In combination with access control systems, license plate identification provides additional benefits. First of all, it is full control over the location of vehicles in the loading area of ​​the enterprise. This makes it possible to track the import of raw materials or the export of finished products, check the efficiency of loading and unloading operations and prevent theft.

At the same time, checking the number of the car not only at the entrance, but also at the exit, excludes the possibility of exporting goods under false or erroneous accompanying documents.

But most of all benefits are received by the owner of the parking lot or parking lot. The automatic license plate recognition system will allow you to control the occupancy of the territory in real time, which will make it possible to take measures to improve efficiency.

Combining license plate recognition with a payment system will completely eliminate the possibility of abuse or theft by employees. And also completely eliminates the possibility of errors in calculating the time spent vehicle on the territory of the parking lot and will give iron proof in disputes with unscrupulous customers.

TECHNICAL CHARACTERISTICS AND COMPOSITION OF EQUIPMENT

The system for automatic license plate recognition, depending on the manufacturer and model, may include several devices and a software complex with modules that perform various analytical functions or serve atypical devices. For example, truck scales, speed radar, etc.

Requirements for the computer on which the program will be installed.

The minimum requirements for different programs can vary significantly depending on the functional load, but in most cases it is necessary:

• processor, not less than 3 GHz;
• video card: Intel, ATI with OpenGL or nVidia at least 512 MB;
• RAM, not less than 4 GB;
• HDD disk with a volume of at least 4 GB.

Video recorder with RTSP function.

It is a streaming protocol that allows not only viewing and recording information, but also using video in real time. An example of such recorders is the HIKVISION DS-7204HVI-SV model.

CCTV camera with RTSP function.

Such devices for recognizing the license plate must have a resolution of at least 550 TVL, which is provided by a 1/3 "760H matrix. The focal length is 9-22 mm, which will make it possible to identify at a considerable distance and at a fairly high speed, for example, Atis AW-CAR40VF or AW-CAR180VF.

The light sensitivity of the camera should be as high as possible from 0.001 Lux, in addition, the device must be equipped with IR illumination enabling high-quality shooting from a distance of at least 15-20 m.

• manual setting of exposure;
• automatic white balance;
• backlight compensation;
• high dynamic range.

These cameras will be used exclusively outdoors, therefore, it is imperative to have an IP 66 enclosure protection class with built-in thermoelements that allow the device to operate at low temperatures of at least -30 ° C.

It is recommended to use black and white cameras, as they have higher sensitivity and resolution than color cameras. In addition, most car license plate recognition algorithms convert the color image received from the camera to black and white.

Executive devices and control modules.

For example, the "BARBOS" module is connected to a PC via a USB connection. This module has 4 five-ampere relays, through which you can control a barrier, gate, wicket, lighting, GSM notification, various indication systems brought to the control room, etc.

CAMERAS FOR RECOGNIZING CAR NUMBERS

The main parameter that you should pay attention to when choosing a place to install CCTV cameras for recognizing license plates is the manual exposure setting. There is a linear relationship between the vehicle speed and the recommended shutter speed (frame exposure time - shutter).

The higher the speed of the car, the shorter the exposure time should be, otherwise the frame will be blurred - motion blur. However, the maximum allowable shutter speed depends not only on the exposure time, but also on the camera angle. The camera angle is the angle between the direction of travel of the vehicle and the optical axis of the video camera.

Most camcorders in the middle price range are capable of transmitting a recognizable image of a license plate with a width of 80 pixels at a vertical angle of installation up to + 30 ° and horizontal angles of deflection of +/- 30 °. A good indicator is considered if the system recognizes the license plate when it deviates from the horizontal (uneven road) +/- 10 °.

The graph of the dependence of the exposure time on the camera installation angle and the vehicle speed is shown in the figure.

Software.

Software - is a key element of the license plate recognition system. There are many development firms offering their product to the consumer.

Most common budget development "NumberOK".

It recognizes Russian, Ukrainian, Belarusian and Moldovan license plates, fixes the date and time of entry and exit of vehicles and the time spent on the territory of the facility. Has the ability to build simple reports and can be integrated into 1C. The program is compatible with most video cameras and DVRs with RTSP function.

The second most important is the license plate recognition system. "Automarshal".

It has 2 recognition algorithms, one for speeds up to 30 km / h, the second - up to 150 km / h. Has specially adapted modules "Parking", "Car wash", "ACS Gate". Ample opportunities for building analytical reports, management via the WEB client and the function of sending SMS notifications.

The vehicle license plate identification system has wider additional capabilities. "Traffic control" research and production association "Discrete".

This program can connect to truck scales and bind gross and net values ​​to the number, as well as generate summaries, balances and other reporting documents. "Traffic control" maintains a photo archive of the moments of vehicles passing through the checkpoint and has wide analytical search capabilities, by car or camera number, time and date.

System "Car number" from the ELVIS Neo Tech company.

The structure includes the modules "Auto-control", "Senesys-Avto" and "Auto Number". The program has significant integration capabilities with other video surveillance systems and access control systems, as well as a flexible report generator, good capabilities for archiving and searching through it.

Undoubtedly, professional license plate recognition systems are quite expensive. And the use of an adapted conventional video surveillance system and demos of specialized software is not as effective as we would like.

But the use of this kind of video analytics is able to bring a business related to by car to a qualitatively new level, both in terms of control and in business analysis.

* * *

© 2014-2020. All rights reserved.
Site materials are for informational purposes only and cannot be used as guidelines and normative documents.