Sign Up
ANPR Software, Misc, Product

Camera Setup for Best ANPR

Automatic Number Plate Recognition, or ANPR, is a great asset to law enforcement, parking management, highway monitoring, gated community surveillance, toll management and other uses.  However, for professionals and hobbyists alike, there are several issues with ANPR camera setup that impedes its accuracy. 

If your license plate reader accuracy rate is at 78 percent rather than 98 percent, then there is hope for you to increase the effectiveness of your system. 

In this article, we will share proven insights from our customers on how to improve your ANPR accuracy rate by making a few modifications to your ANPR camera setup and system.    

What is ANPR?

ANPR is automatic number plate recognition, also known as Automatic License Plate Recognition (ALPR) in some countries. It is a system that is capable of reading vehicle number plates directly from the camera, from inside the camera or from images captured by the camera.

As this industry expands, it has become important to note that there are factors that impact its success. When ANPR accuracy rates are suboptimal, it is common to blame the underlying ANPR engine.

Factors Impacting ANPR Success 

There are a number of fundamental components that make ANPR successful.  These include:

  • The camera itself, such as the resolution, IR capabilities, etc.
  • Camera setup, such as the angle of placement, zoom/pan, etc.
  • ANPR engine, such as the underlying algorithms to identify vehicles and plates.

Of these three, we see that camera setup holds the most potential for improvement for businesses and consumers to significantly bolster their ANPR results.  

We draw this conclusion because we know that our Plate Recognizer ANPR engine has been thoroughly tested and optimized to handle blurry, low-res, and dark images as well as other aspects of the real-world environment.  Feel free to reference the results of our ALPR benchmarking exercise. 

Further, counter to claims from camera manufacturers, we see that a modest, mid-range IP camera performs just as well as a high-end, expensive camera.  Now, of course, no LPR camera vendor is going to admit this because they need a way to justify their existence. 

From our years of experience supporting and helping clients troubleshoot their license plate recognition systems, we have observed how proper camera setup along with a strong ANPR engine can be an effective solution to detect and decode vehicle license plates. 

This article offers specific tips and suggestions on how to best set up your camera to maximize your ANPR.

Camera Zoom for Best ANPR

For beginners handling license plate recognition, there is a common misconception that a wide-angle shot is the best.  Cameras will seek to aim wide across parking lots rather than towards entrance or exit points, which allow them to truly pick up plates and get a good read. 

This is a simple fix if you know how to fix it. Adjust the camera positioning and width of the focus so that the license plate is picked up in the shot, and you’ll instantly have greater accuracy. Rather than have a wide-angle view of the street with all the homes around it, it is better to focus on just the street itself.

In the photo below, you can find the image with the red box showing the plate. If the camera was zoomed in closer to the gate, the focus would improve. Make sure you are not over-zooming because you’ll need about 100 pixels of width on the license plate in order to get a good LPR read.

If you are in an area using CCTV cameras, Plate Recognizer’s software may still work. While CCTV cameras are typically on the lower end of the quality spectrum, they may still be suitable to capture vehicles moving at low speeds.

Camera Setup Best ANPR Zoom

Zooming into the vehicle yields stronger ANPR accuracy as compared to taking a wide-angle view of the area. Source: Plate Recognizer Clients.

Camera Distance for Better ANPR

The maximum advisable distance between the camera and the vehicle is 35 meters.  Actually, whenever possible, it is preferred to minimize that distance.  Why?  Because minimizing the distance between the camera and vehicle helps ensure that the camera can easily focus without the need to zoom in to the target vehicle.  This helps reduce image blurriness.

When you place the camera far away from the vehicles it needs to read, you will need a camera with very strong zoom capabilities. The more the camera uses the zoom, the harder it is for the images to come out clear and crisp. 

Another cause for blurry images can be if the camera is mounted improperly, or becomes loose. Typically, ANPR cameras are outdoors and exposed to the elements so this is going to happen at some point if the cameras aren’t installed securely. This can cause the camera to move, shake or vibrate.  These small vibrations can result in image blurriness when the zoom level is high.  

Not convinced?  Use your smartphone camera and zoom in all the way to view a car in the distance.  Apply a small amount of movement to the camera and see how the camera view totally changes!

PRO TIP: Before you set up the camera, use a mobile phone as a test subject. Place the phone in the position of where you intend to install your ANPR camera. Set the smartphone to the number of pixels and settings of the camera you plan to purchase.  Then, just record 10 minutes of footage and use Stream to analyze the recorded video for license plate recognition.

Camera Setup Best ANPR Distance

Distance between camera and vehicle should be minimized as much as possible and definitely under 35 meters. Source: Plate Recognizer.

Camera Angle to Improve ANPR

While Plate Recognizer ANPR has been tuned to support a wide variety of license plate angles, it’s always ideal to have the camera set up appropriately. In terms of angle, the setup of the ANPR camera can be positioned in two ways, slope as well as vertically and horizontally.  For both cases, it is advisable to have a maximum of 45 degrees for a proper read of the license plate. 

ALPR vendors can make outrageous claims that their software can do anything, but at Plate Recognizer, we’re not going to lie to you. There are things our software can do, and things it can’t!  Not every angle is going to be possible, and no camera is going to be a super machine that can see a license plate while bending over backwards in the middle of a blizzard. 

So for example, Plate Recognizer’s ALPR engine can support up to a 53 degree tilt, and a 70 degree side angle. What it can’t do is catch a plate number at 75 degrees.

In fact, we’ve compiled real world ALPR results.  Take a look

Camera Setup Best ANPR Vertical Angle

Vertical angle of camera on vehicle license plate should be under 45 degrees. Source: Plate Recognizer.

Camera Setup Best ANPR Horizontal Angle

Horizontal angle of camera on vehicle license plate should be under 45 degrees. Source: Plate Recognizer .

Minimum Resolution for Best ANPR

We see a lot of unsuccessful LPR due to very fuzzy images of the license plate.  This is by and large due to the fact that the camera does not have the resolution required to capture a good plate image.

While Plate Recognizer works with any IP camera, we recommend that the license plate itself must have roughly 100 pixels in width.  Otherwise, our ANPR engine may not be able to effectively read the license plate.

Since every LPR camera setup will be different, you’ll need to figure out the correct amount of megapixels (MPs) needed.  Basically, the number of megapixels required will ultimately depend on the distance of the camera to the license plate.

The width of the license plate will depend on the country you’re in.  Here are some examples:

  • United States: 305 x 152 mm (12 x 6 inches).
  • Europe: 520 x 110 mm (20.5 x 4.3 inches).
  • Brazil: 400 x 130 mm (15 x 5 inches).

Once you have an idea of the width of plates for your ANPR camera setup, you’ll need to figure out the MPs needed. There’s a bit of math here to calculate, so we’ll  save you the headache and go straight to the answer.  

The table below summarizes the maximum distance in feet from the camera to the vehicle plate for each of the 3 major regions/countries.  You’ll note that we used 80 pixels of width for the plate, even though our ALPR benchmarking indicates that our engine can read a plate even at 30 pixels width.  We chose 80 pixels width to add some cushion–just to be on the safe side.  

Install Camera Best ALPR Camera Distance License Plate

Above analysis utilizes 80 pixels for width of license plate. Source: Plate Recognizer.

So net net, if you have to set the camera up at over 30 feet from the vehicle plate in the USA, then you’ll need to get a 4 MP camera or better.

PRO TIP: If the above topic on camera resolution is confusing, no worries.  Just use your eyes!  Basically, if you can see the license plate number in the camera footage with your own eyes, then Plate Recognizer’s engine should be able to read the plates, too. But if you’re having a really hard time seeing the plate–even after squinting and zooming in–then please don’t expert Plate Recognizer to do magic.

Sufficient Infrared for Good Night-time ANPR

If you have a great ANPR system, but no infrared (IR) light capabilities, you will have a tough time capturing plate numbers at night. This is because when it’s dark, there’ll be glare on the plate from the headlights.  If you’re using ANPR to detect crime, it most often will happen at night so without good infrared lighting, you won’t be able to get the information needed from your ALPR camera.

Infrared cameras utilize LED lights to illuminate the plate area with infrared light, which is invisible to humans.  Cameras with an IR cut filter automatically adjust IR light levels so that you can get consistent colored images in the day time and black/white images at night.

Depending on the exterior lighting, you may be able to get a license plate read at night without IR, but it won’t have the same accuracy. Using IR may also help you pick up images in different weather conditions. For example, if you are in a location that gets a lot of rain, an ANPR system that relies on white and natural light will have a hard time getting accurate images. 

For optimal IR use, you’ll want to place the camera on an angle so it isn’t pointing directly at headlights. This will avoid unnecessary glare risks and ensure you’re getting a good shot of the license plate. 

If your current lpr camera doesn’t have IR, you can always buy a cheap external piece instead of upgrading your entire system. The IR technology built into a camera may also not be enough, so adding another external device can increase accuracy.

Camera Installation Best ALPR Infrared

Image without (left) and with (right) infrared.  IR can make a big different for night-time LPR reads. Source: Plate Recognizer.

Camera Frames May Impact ANPR

The camera frame (and thus your ANPR camera setup) is largely based on the vehicle’s speed. If you’re looking to capture license plates that are still versus license plates that are moving (also called “free flow”) then the specifications for altering your camera will be different. 

You will need to calculate the net difference in speed. If your camera is in a fixed position, then the net speed is the speed of the vehicle. If the camera is maintained in your vehicle (e.g. police car), and then you’re driving the same direction of the target vehicle, then the net speed is the difference in your speed and the target vehicle’s speed. Keeping this in mind prevents you from having any unusable images because you didn’t take the time to equip your camera for the proper camera speed.

When setting up an ALPR camera in areas where vehicles are moving really fast, you’ll want to use Stream instead of Snapshot. This is because Steam is going to, well, stream the footage and Snapshot gives you individual images. When the Batmobile is blasting by, one Snapshot will most likely be blurry.  Stream utilizes several different algorithms to identify fast moving vehicles and find the optimal capture time to get license plate information.

With Stream, you have the ability to customize the speed at which the software is working to better capture moving vehicles. Here are our minimum effective FPS recommendations for ALPR when using Stream:

  • For vehicles traveling < 30 mph, set the eFPS to 4-5.
  • For vehicles traveling 30-60 mph, set eFPS to 8-10.
  • For vehicles traveling > 60 mph, set eFPS to 12.

Basically, the faster the vehicle is traveling, the more frames you’d need Stream to process.  This way, our ANPR engine has more opportunities to evaluate and decode the license plate as the vehicle passes a certain point.  Now, there’s no harm in over-processing more frames–especially if you have a sizable machine to run Stream.  But if you under-process the frames, then you may end up missing some vehicle plates.  

Camera Installation Best ALPR FPS

If eFPS is not set appropriately, you’ll get a blurry image. Source: Plate Recognizer.

Camera Lighting for Better ANPR

While Plate Recognizer has greatly improved its algorithms to support dark images, it is nevertheless a good idea to ensure that the camera is set for the right lighting conditions.  You can adjust the camera shutter speed accordingly so as to not to over-expose or under-expose the image.  For example, if it is bright outside, adjust the shutter speed to capture at 1/5000 of a second.  At night time, set the shutter speed to 0.75 to 1 second.  

If the camera does not auto-adjust the shutter speed based on the outside lighting conditions, then you can try to have a light fixture directed towards the entering vehicle.  This way, there will always be adequate lighting on the vehicle.

Camera Setup Best ALPR Ligthing

Ensure adequate lighting to avoid over-exposed or under-exposed images. Source: Plate Recognizer.

Detection Zone to Improve ANPR

The trickiest part of LPR camera setup is making sure nothing is in the way of getting that image. Cameras are smart, but they need assistance to make sure they’re capturing the right thing. This is where ANPR Detection Zones can help with your camera setup. 

For example, if your LPR camera is set up on a two-way street, you can use our Detection Zone feature to mask or block off the south-bound traffic because you only care about the north-bound traffic.  You can also use the Detection Zone feature to instruct the ALPR engine to ignore the street sign, the Drive Thru sign, etc.

Shouldn’t Plate Recognizer be smart enough to ignore these street signs?  Yes!  We have actually spent a tremendous amount of time and effort fine-tuning our neural networks to ignore false positives (e.g. street signs, bumper stickers, signs on cars).  So using the Detection Zone feature can help give you an added assurance that the accuracy of the plate reads are maximized.

Detection Zone can be accessed directly through the Plate Recognizer Software.You can use Detection Zone on Snapshot Cloud, Snapshot SDK and Stream. All you’ll need to do is simply upload the image from your LPR camera and enter the correct Camera ID. Once you’ve uploaded the image, you can click add zone. Then you’ll be able to use the masking markers to create a template for your zone.

Install Camera Best ALPR Detection Zone Mask

Detection Zones are easy to set up and can help reduce false positives in LPR results. Source: Plate Recognizer.

Set Region to Improve ANPR

Another important thing to consider when setting up your LPR camera is the country or state you’re in. Depending on where you live, a zero might look like letter O, or the other way around. Making sure your LPR camera is set to the appropriate state will greatly reduce the risk of error. 

Also consider that vehicles from other states and even countries could end up being captured on your LPR camera.  In this situation, just add multiple regions (country or state) and prioritize the list based on which region you expect the most amount of vehicles to be from. 

If you’re setting up ANPR in Germany, you can use our special German and Austria engine to recognize umlauts and spaces. Or, for ANPR in Thailand, use our special Thailand engine.  

Otherwise, you can use our single engine, which covers 90+ countries around the globe.  For added pleasure, feel free to read about our ALPR for USA, Brazil, and India!

Camera Installation Best ALPR Set Region

Can you tell which is a zero or a letter O?. Source: Plate Recognizer.

Engine Improvements Keep ANPR Up to Date

One of the saddest notes in this space is that companies rarely update their ALPR engine.  Some do updates once or twice a year, or maybe not at all.  This means that the ALPR technology can become outdated quickly, resulting in inaccurate readings, etc.

Here at Plate Recognizer, we deliver a new version of our ALPR engine every 3-6 weeks. ALPR updates include new features, fine-tunings in the engine, new plate formats, stronger make-model analysis, and more!

Use Color to Improve ANPR

To color or not to color?  This is an easy one.  Just like how the eye can decipher an image more clearly with color, the LPR camera should set with color, not monochrome.  

Also, our Vehicle Make Model Color engine works much better with a color image or camera feed.  Why?  Because the engine can more easily identify the vehicle logo, calculate the width of the headlights relative to the width of the car, etc.

Install Camera Best ALPR Color Monochrome

Always better to use color images. Source: Plate Recognizer.

Additional Tips to Improve ANPR

While there’s plenty that you should do, there’s also plenty that you should not do. Let’s face it. Cameras come with a lot of settings, and it’s easy to switch on a bunch of settings that you either don’t know what they are or don’t need and forget that you’ve activated. Here are some to keep in mind:

Automatic gain control (AGC), digital noise reduction (DNR), autofocus, and back light compensation (BLC) are all features you want to keep disabled while enabling ANPR camera setup. Once again, this is because it will give you the best chance of grabbing that license plate number from a moving vehicle using ANPR. 

AGC creates issues because the gain itself prompts digital noise and lower recognition in the image. It’s often much simpler just to leave the feature off. DNR is best left alone because it is performed by removing pixels based on comparing two frames. Although this might seem harmless, it’s often not because it can easily remove pixels that could be helpful to you in the future. Next, you can pass on autofocus because adjusting the sharpness often reduces the recognition quality in the image itself. Finally, the BLC can cause issues with the image because it often occurs when a light source enters a frame. When the pixels do not have enough time to properly adjust, the camera will not be able to capture a good image. 

And, while this may seem obvious, we see that the best ANPR contains images that are in landscape rather than in portrait view.  This makes intuitive sense, since the license plate itself is often oriented in landscape than portrait mode.  And, just like watching TV, we (and thus our ANPR engine) is used to seeing the world in a landscape format.  

Think About End in Mind for Best ANPR

When considering a LPR camera set up, think about what you plan to do with the results. That will give you a better understanding of how to set up your system. There’s a lot you can do with Plate Recognizer and ParkPow (sister company), such as:

  • Search through a database of stored plates.
  • Get alerts when certain vehicles are detected.
  • Track length of time cars are parked in your parking lot.
  • Import vehicle data from third-party systems.

For more on this topic, read our 5 Tips Before a License Plate Reader Camera.  

Conclusion

Following the best practices discussed in this article can be the difference between an ANPR accuracy of 75 percent and 98 percent. In many cases, it’s just as much about knowing what to do as it is knowing what not to do so that you can get the best ALPR results to meet your business and personal goals

You Can Help!

Have some good real-life examples of camera setup best practices for ANPR? Contact us and share!  We’d love to include your insights into this article.

Contact Us

Have a question about ALPR or Parking Management Software? Contact Us

About Plate Recognizer

Plate Recognizer provides accurate, fast, developer-friendly Automatic License Plate Recognition (ALPR) software that works in all environments, optimized for your location. Sign up for a Free Trial!