Nvidia’s accelerated computing has helped India manage toll booth traffic, which amounts to four million miles and covers 1,000 toll booths.
India’s road network is the world’s second largest, and most of it is manually operated. Established toll booths, wherever they are located in the world, can contribute to massive traffic delays, long commutes, and earnest traffic jams.
To facilitate automate toll booths across India, Calsoft, an Indian-American technology company, helped implement a wide range of Nvidia technologies integrated with the country’s dominant payment system, known as the Unified Payments Interface, or UPI, for one of its clients.
Manual toll booths require more time and labor compared to automatic ones. However, the automation of India’s toll collection systems comes with an additional complication: the variety of license plates.
Join us at GamesBeat Next!
GamesBeat Next is bringing together the next generation of video game thought leaders. And you can join us, October 28 and 29 in San Francisco! Take advantage of our buy one, get one free offer. The sale ends this Friday, August 16. Join us by registering Here.
Non-standard number plates in India pose a significant challenge to the accuracy of automatic number plate recognition (ANPR) systems. Any implementation would need to account for these differences in number plates, which include different colors, sizes, font styles and placement on vehicles, as well as multiple different languages.
The solution, which Calsoft helped build, automatically reads the license plates of passing vehicles and collects the fee from the UPI account of the associated driver. This approach reduces the need for manual toll collection and is a huge step towards solving the region’s traffic problem.
Automation in action
The solution has been piloted in several leading metropolitan cities. The solution achieves around 95% accuracy in license plate reading by using an ANPR pipeline that detects and classifies license plates as they pass through toll booths.
According to Vipin Shankar, senior vice president of technology at Calsoft, Nvidia technology was key to the effort. “Night detection was particularly challenging.
“The next challenge was to improve the model’s accuracy in terms of pixel distortions caused by environmental factors such as fog, heavy rain, reflections from bright sunlight, dusty winds, and others,” he added.
The solution uses Nvidia Metropolis to track and detect vehicles throughout the process. Metropolis is an application framework, developer toolkit, and partner ecosystem that combines visual data and AI to improve operational efficiency and safety across multiple industries.
Calsoft engineers used Nvidia Triton to deploy and manage AI models. The team also used Nvidia DeepStream’s software development toolkit to build a real-time streaming platform. This was key to efficiently processing and analyzing the data streams, including advanced capabilities like real-time object detection and classification.
Calsoft uses Nvidia hardware, including Nvidia Jetson Edge AI modules and Nvidia A100 Tensor Core GPUs in its AI solutions. Calsoft’s toll booth solution is also scalable, meaning it’s designed to meet future growth and expansion needs and can better ensure consistent performance and adaptability as traffic conditions evolve.