How India uses Nvidia computers to reduce traffic

Nvidia’s supercomputers will help India manage traffic, which passes four million through 1,000 tollbooths.

Tne Indian road network is the second largest in the world, and most of it is manually operated. Tollbots, wherever they are in the world, can contribute to traffic delays, longer travel times and more traffic congestion.

To help tollbooths in India, Calsoft, an Indian-American technology company, helped implement Nvidia technology integrated into the country’s main payment system, known as the unified payment system, or UPI, for customers.

Manual checkouts require more time and labor compared to automated checkouts. However, automated payment systems in India face another challenge: different types of licenses.

India’s non-standard number plates pose a major challenge to the accuracy of ANPR systems. Each implementation must deal with the diversity of these plates, which include different colors, sizes, color styles and placement on vehicles, as well as different languages.

Calsoft’s solution helped make it possible to automatically read license plates and charge the driver’s UPI account. This system reduces the need for manual toll collection and is a major step towards reducing traffic congestion in the area.

Automation in Action

As part of a pilot program, this solution has been deployed in several leading cities. The solution offers 95% accuracy in its ability to read plates using an ANPR pipeline that detects and places plates as they pass through tollbooths.

Nvidia’s technology has been key to this effort, according to Vipin Shankar, vice president of technology at Calsoft. The hardest thing was to notice at night.

Another challenge was to improve the accuracy of the model for pixel distortions due to environmental damage such as fog, heavy rain, glare from sunlight, dusty winds and more,» he said.

The solution uses Nvidia Metropolis to track and detect traffic throughout the process. Metropolis is an operating system framework, software development tool and collaborative solution that brings visualization and AI together to improve operational efficiency and security across a variety of industries.

Calsoft engineers used Nvidia Triton to deploy and control their AI models. The team also used Nvidia’s DeepStream software development tools to create a real-time streaming platform. This was essential for processing and analyzing data streams effectively, including advanced capabilities such as real-time detection and classification.

Calsoft uses Nvidia hardware, including Nvidia Jetson modules for edge AI and Nvidia A100 Tensor Core GPUs in its AI solutions. Calsoft’s tollbooth solution is also scalable, meaning it is designed to accommodate future growth and development, and can ensure consistent performance and adapt to changing traffic conditions.