Listen to this story
Industry.AI, a member of the NVIDIA Metropolis vision AI partner ecosystem, has deployed its vision AI platform across Bengaluru’s recently built terminal, T2, known as the Garden Terminal. It’s a debut at scale for intelligent video analytics at an Indian airport. CEO Tejpreet Chopra revealed that Industry.AI plans to deploy NVIDIA-powered accelerated computing and vision AI across other terminals as well as at additional airports.
Annually around 32 million people travel through the Indian Silicon Valley’s airport making it an important destination for deploying emerging technologies. In December 2022, the newly launched T2 became one of the first terminals in the world to be experienced on the metaverse.
Industry.AI’s platform is capable of tracking abandoned baggage, identifying long passenger queues, and real-time alerts for security concerns.The platform connects 500+ live camera feeds across the terminal to accomplish nearly a dozen tasks in real time via vision AI. For example, the system can detect unattended luggage or personal items. Furthermore, it helps forming passenger lines at terminal entrances, check-in points, security screenings, and other key zones.
“Deploying vision AI at this scale is a first for us,” said George Fanthome, chief information officer at BLR’s parent company. “By adopting such advanced deep learning technologies, we strive to be one of the best airports in the world and provide our customers the best experience.”
Real-time monitoring also notifies platform users about unauthorised individuals and vehicles within the airport premises. Moreover, Industry.AI detects speeding vehicles outside the terminal to oversee secure transportation around the hub.
Industry.AI uses a combination of NVIDIA’s TAO Toolkit and A100 Tensor Core GPUs to train its AI models. The company’s AI inference operations are seamlessly facilitated by NVIDIA’s Triton Inference Server coupled with A30 Tensor Core GPUs. Furthermore, Industry.AI has integrated NVIDIA’s DeepStream sdk for AI-enhanced video analytics. The initiative was completed within a span of a merely three months.