Nvidia’s high-speed computing Helped India manage Toll traffic passes through 1,000 toll booths and covers 4 million miles.
India has the second largest road network in the world and most of it is manually operated. Traditional toll booths, wherever they are located in the world, can cause massive traffic jams, long commutes and severe road congestion.
To help automate toll booths across India, Indo-US technology company Calsoft helped implement a range of Nvidia technologies for its client that are integrated into the country’s primary payments system, known as the Unified Payments Interface (UPI).
Manual toll plazas take more time and effort than automated ones, but automating India’s toll plaza system faces an additional complication: the variety of license plates.
Join us for GamesBeat Next!
GamesBeat Next is the event that connects the next generation of video game leaders. Join us on October 28th and 29th in San Francisco. Take advantage of our buy-one-get-one-free offer. The sale ends this Friday, August 16th. Register to attend. here.
India’s non-standardized number plates pose a significant challenge to the accuracy of Automatic Number Plate Recognition (ANPR) systems. Implementations must address the variations in these plates, including different colors, sizes, font styles, placement on the vehicle, and different languages.
The solution Calsoft helped build automatically reads the license plates of passing vehicles and charges the associated driver’s UPI account. This approach reduces the need for manual toll collection and marks a major step toward addressing the region’s traffic issues.
Automation in Practice
The solution, which is being deployed in several major metropolitan areas as part of a pilot program, increases license plate reading accuracy to approximately 95% by using an ANPR pipeline to detect and classify license plates as they pass through toll booths.
Vipin Shankar, senior vice president of technology at Calsoft, said Nvidia’s technology was crucial to the effort: “Nighttime detection was particularly challenging.
Another challenge was to improve the model’s resistance to pixel distortion caused by environmental effects such as fog, heavy rain, bright sunlight reflections and dust-blowing winds,” he said.
To track and detect vehicles throughout the process, the solution uses Nvidia Metropolis, an application framework, set of developer tools and a partner ecosystem that combines visual data with AI to improve operational efficiency and safety across a range of industries.
Calsoft engineers used Nvidia Triton to deploy and manage the AI models, and the team also used the Nvidia DeepStream software development kit to build a real-time streaming platform, which was key to incorporating advanced capabilities such as real-time object detection and classification to efficiently process and analyze data streams.
Calsoft uses Nvidia hardware, including Nvidia Jetson Edge AI modules and Nvidia A100 Tensor Core GPUs, for its AI solutions. Calsoft’s toll booth solutions are also scalable and designed to accommodate future growth and expansion needs, better ensuring sustained performance and adaptability as traffic conditions change.
