VNPT Advances Traffic Safety With NVIDIA AI Enterprise


Vietnam Posts and Telecommunications Group (VNPT) is one of the largest telecommunications and digital technology companies in Vietnam. They provide a wide range of services related to telecommunications, postal services, and information technology. The Innovation Center at VNPT is responsible for developing and expanding VNPT AI, which includes creating new AI products and services and improving existing ones to maintain the company’s competitive edge and meet evolving customer needs.

One of VNPT’s initiatives was to improve road safety in the nation’s busiest intersections using the power of AI.


Vietnam Post and Telecommunications Group (VNPT)



Use Case

Computer Vision / Video Analytics


NVIDIA AI Enterprise
NVIDIA-Certified Systems

Tapping Into Thousands of Video Streams

As road traffic continues to increase significantly, VNPT wanted to find a way to improve congestion and both driver and pedestrian safety with real-time traffic monitoring. To do this, they needed extremely accurate, high-performance AI models to handle hundreds of thousands of AI service requests on thousands of cameras across Vietnam. Leveraging NVIDIA accelerated compute, VNPT launched a computer vision AI project to develop and deploy a sophisticated traffic monitoring system involving thousands of cameras. 

A crucial part of this solution involved NVIDIA DGX™ A100 for training, NVIDIA T4 and A30 Tensor Core GPUs for inferencing, and NVIDIA AI Enterprise for developing vision AI applications and delivering AI services to VNPT’s customers. The software layer of the NVIDIA AI platform, NVIDIA AI Enterprise includes over 100 frameworks, pretrained models, and development tools from NVIDIA Metropolis such as the NVIDIA DeepStream SDK and NVIDIA® TensorRT™. Metropolis is a highly versatile, end-to-end AI-powered video analytics platform that enables developers to build AI models for real-time video streaming.

A Computer Vision Network Built by NVIDIA AI Enterprise

VNPT used NVIDIA Metropolis to process and analyze multiple video feeds from strategically placed cameras around some of the most traffic-heavy intersections in major cities. Using containers included with NVIDIA AI Enterprise, the AI models were trained with NVIDIA pretrained models, frameworks, and TensorRT and integrated with DeepStream to detect, recognize, and classify objects such as cars, motorcycles, bicycles, and pedestrians. The video analytics applications are deployed at the edge with NVIDIA Jetson™ or on premises with T4 and A30 GPUs. 

The edge cameras, combined with Jetson and pretrained models, were programmed to understand and interpret traffic signals, track the movements of identified objects, and predict potential incidents based on observed patterns. Multiple concurrent video streams are also processed on the backend servers, saving compute and operational costs. 

Since it was their first time using the DeepStream SDK, VNPT initially had some challenges and experienced performance issues. With NVIDIA AI Enterprise licenses, they were able to engage NVIDIA Enterprise Support for help. VNPT solved their performance issues, set up an effective AI training system, and optimized the performance of their AI services with the help of NVIDIA AI experts. 

“NVIDIA AI Enterprise, including NVIDIA DeepStream, has been instrumental in achieving our goals. With it, we have demonstrated how AI can be effectively harnessed to address real-world issues and improve the quality of life in our cities,” said Nguyen Tien Cuong, CEO of VNPT AI.

“VNPT received excellent support from NVIDIA experts to set up and optimize the AI models, resolve issues, and enhance infrastructure performance in an optimal manner,” explained Cao Thanh Ha, CTO of VNPT AI.

Smoother Traffic, Safer Roads

With the successful implementation of this solution, VNPT AI has not only increased safety for drivers and passengers but also optimized traffic flow. The AI-driven system provides real-time insights about traffic congestion and highway situations, allowing authorities to respond to incidents quickly and efficiently.

By monitoring traffic, identifying potential hazards, and alerting necessary response teams, the system can effectively prevent accidents and contribute to a safer, more efficient transportation environment for locals.

Using the tools and frameworks included with NVIDIA AI Enterprise, VNPT AI saved on both model training and application development time. This allows the data science team at the Innovation Center to focus on AI model optimization, localization, and new project development, while producing faster and higher-quality models. By quickly developing AI products, VNPT can deliver the latest solutions to their customers. Looking toward the future, VNPT plans to leverage NVIDIA AI Enterprise to develop additional AI products and services, including chatbots and process automation.

“VNPT received excellent support from NVIDIA experts to set up and optimize the AI models, resolve issues, and enhance infrastructure performance in an optimal manner.”

Cao Thanh Ha
Chief Technology Officer, VNPT AI



Ready to kick-start your enterprise AI journey?
Learn more about NVIDIA AI Enterprise.