In November, highway concessionaire PLUS Malaysia announced it had rolled out automated number plate recognition (ANPR) to track vehicles passing through North-South Highway toll plazas. The system is meant to ensure motorists are paying their toll fees as they should and is said to be the first step towards the goal of multi-lane free flow (MLFF), a form of open road tolling that dispenses with the usual booths.
Now, technology giant Nvidia has detailed the computer vision and artificial intelligence (AI) tech found in PLUS’ ANPR system, which incorporates the company’s proprietary graphics processing units (GPUs) and software. VehicleTrack, developed by Malaysian startup Tapway, can read a number plate and detect a car’s class, make and colour in just 50 milliseconds – even when it’s travelling at up to 40 km/h.
Founded by former aerospace engineer Lim Chee How, Tapway entered into the project by responding to a call for help in video analytics back in 2019. The client, PLUS, was looking to be able to effectively track a car’s entry and exit points, given that the North-South Highway runs a closed system for tolls.
Specifically, the company wanted to prevent users from using one payment method to enter the highway and another to exit, presumably in preparation of its rollout of Touch ‘n Go’s radio frequency identification (RFID). This was meant to stop motorists from either trying to cheat the system or being double charged. “We showed them how with computer vision — just a camera and AI — you could solve all that,” said Lim.
Tapway trained and ran its AI models using Nvidia A100 and V100 Tensor Core GPUs; the result is a system that works in all light and weather conditions with a consistent 97% accuracy, Nvidia said. Each GPU can manage up to 50 video streams at once thanks to an Nvidia Triton Interference Server, enabling the ANPR system to process up to 28,800 images a minute on edge servers using Nvidia A10, A30 and T4 GPUs.
“Triton is a real lifesaver for us,” said Lim. “We had some scaling problems doing inference and multithreading on our own and couldn’t scale beyond 12 video streams in a server, but with Triton we easily handle 20 and we’ve tested it on up to 50 simultaneous streams,” he said.
According to Lim, Tapway uses a dataset of up to 100,000 images to prepare a new AI model for a customer in just a few hours, rather than several days in the case of a CPU-based system. The company builds its apps using the Nvidia DeepStream software development kit (SDK) and optimises its AI models via TensorRT, an SDK for high-performance deep learning inference.
As we’ve previously reported, PLUS uses the ANPR system not only on RFID lanes, but also Touch ‘n Go and SmartTAG ones. This enables it to track all users, even if they enter using a TnG card or SmartTAG and exit using RFID, charging their eWallet (via RFID) rather than their card. The company has installed 577 cameras so far and plans to grow this number to nearly 900 at 92 toll plazas, Nvidia said.
Even with all this technology, PLUS’ ANPR system is not foolproof. To that end, the concessionaire has implemented a dedicated validation centre where backend staff are able to augment the system by identifying damaged, dirty or non-standard (i.e. with “fancy” fonts and spacing) plates.
Since its founding in 2014, Tapway has implemented 3,000 sensors in 500 locations throughout Malaysia and Singapore. Its AI tech not only detects number plates but also help study consumer buying habits in malls; the company even wants to aid regional carmakers and palm oil producers in improving quality control inspections, Nvidia said.
Looking to sell your car? Sell it with Carro.
97% accuracy is not good enough. Just imagine every 100 cars, 3 cars is wrongly detected. Just imagine more than 1 million cars on the road and 30000 carsis wrongly detected. If the authority is so proud of 97% accuracy. You are deadly wrong !
You tell me which man made products got 100% accuracy?
Of course no one expects 100% accuracy.
But 97% and 99.99% (which is an expected and accepted accuracy rate when it comes to digital technology) means error of 30,000 vs 100 per million toll passes.
PLUS estimates 2 million per day so 200 is a realistic, manually fixable error and should not be a problem for motorists.
More congestion at tolls
Not even Elon can guarantee you Autopilot works 99.99% of the time so what bullshit is this about.
Mysejathera
What is your academic qualification?
Siz sigma heard it before? it is 99.99966%. Mean 10,000,000 alowed 34 defects.
If 97% from 10,000,000, it will produce 300,000.
Still can not imagine? What is the feeling for having only RM34 in your bank account and RM300,000 in your bank account?
No one will allowed 3% defects in their process desgin!!!
Friend. Only highly automated semicon industry could follow Six Sigma to micro digits, everywhere else are talking Six Sigma in the hundreds or thousands. Bear in mind these are only applicable to highly controlled environments and such like a factory. When applied in open environments and variable challenges, Six Sigma does not apply.
Wondering if his/her spouse applying that 6σ. Must be ‘happily’ ever after.
3% are fancy plate user
sem
bang
kuad
charge me money, but the palang dont open. apa system ini
if detect wrongly, who will be charged?
What about someone using the fake number plate?
how to ensure the number plate is the rightly registered with the rightful owner?this is one of the reason singapore/japan utilize an In-vehicle unit.. not to mention fake plates are everywhere in malaysia, including driving license.
Lets say express bus with plate number: JRB123 travel round trip daily from Johor-Penang and Penang Johor. If the system not accurate and detected as JR8123. I think the actual vehicle owner for JRB123 will cry after 1 week. Pls use more reliable solution instead of this kind of 97% system.
Talk, talk and talk. Rfid is in operation now. My experience with rfid so far is far worst than smart tag, and not seeing any improvement.
My experience with RFID is far better than Smart Tag or TNG card. So each has their own opinion, does not mean the system is worse than the other but RFID is the future so why stay with an outdated system.
Then people can use different number plates to charge somebody else
“PLUS uses the ANPR system not only on RFID lanes, but also Touch ‘n Go and SmartTAG ones”
“PLUS uses Tapway AI, Nvidia GPUs for automated number plate recognition (ANPR) for RFID toll tracking”
Paultan. Can you correct the title please? Why not say “PLUS uses Tapway AI, Nvidia GPUs for automated number plate recognition (ANPR) for SmartTag toll tracking”? Because this will offend your friend? But you are ok with misleading the public with the current title?
The image quality looks like it comes from nokia sabun phone VGA camera
For kelapa sawit recording…