London, UK and Santa Clara, US — April 8th, 2021 — SKY ENGINE AI, a UK-based data science technology company that develops innovative software used for artificial intelligence and computer vision, today announced it has joined the NVIDIA Metropolis Partner Program.
SKY ENGINE AI — Deep Learning in Virtual Reality with Sensors Fusion and Simulations for Computer Vision in Smart Cities and intelligent video analytics with AI drones.
SKY ENGINE AI is leveraging its Software-as-a-Service (SAAS) platform for Deep Learning in Virtual Reality, powered by NVIDIA GPU acceleration, for developers building and deploying smart city applications with NVIDIA Metropolis ecosystem.
The NVIDIA Metropolis platform allows companies to create complete solutions for video capture, processing, storage, and visualization — from the edge to the cloud. The partner program offers system design tools and turnkey software packages enabling pre-validated, enterprise-ready intelligent video analytics (IVA) solutions that can be deployed to build smarter and safer cities worldwide.
The primary challenges are that AI-training data acquisition is very costly and time consuming, human-based labeling introduces errors, and accuracy of the deep learning models is affected by the insufficient, unbalanced data and prolonged time needed to improve the deep learning models.
SKY ENGINE is designed to address these challenges. Its AI engine can generate data using a proprietary, dedicated rendering system, and images come already labeled and ready for deep learning. The rendering system is tightly coupled with a deep learning pipeline to assure the evolution of Sky Engine. During the training, Sky Engine can spot ambiguous situations that deteriorate the accuracy of the AI model and asks the renderer to provide more imagery data to reflect problematic situations that the deep learning could improve. Also, SKY ENGINE improves with every conducted experiment. Moreover, SKY ENGINE supports not only precise simulations of visual light, but also other modalities like X-rays (for medicine or security), near-infrared (security), and Lidar and radar (aerospace, military, archeology).
The NVIDIA Metropolis IVA platform spans multiple products operating on a unified architecture. It enables the creation of smarter spaces by applying deep learning to video streams for applications such as public safety, traffic management and resource optimization.
SKY ENGINE AI will leverage its Deep Learning in Virtual Reality platform that enables synthetic data generation for Computer Vision AI models training in Smart City application and intelligent video analytics with AI drones across multiple industries with NVIDIA Metropolis.
The NVIDIA Metropolis platform brings businesses, cutting-edge technology, and the developer ecosystem together to create, deploy, and scale IoT applications from the edge to the cloud. It provides a powerful new foundation for frictionless retail, streamlined inventory management, traffic engineering in smart cities, inspection on factory floors, and more.
SKY ENGINE AI joins hundreds of NVIDIA AI City partner companies that are already providing powerful products and applications using deep learning on NVIDIA GPUs. SKY ENGINE AI is providing two example solutions developed in its proprietary platform: telecommunication network performance optimization and infrastructure audit (i.e. 5G antennas detection), and sport analytics based on rugby games.
Smart and Safe Cities need SKY ENGINE AI — The very first evolutionary AI engine designed for deep learning in virtual reality for computer vision applications. Here (Left) rugby game deep insights for analytics, and (Right) 5G network performance optimization case — 3D telecom antenna detection and monitoring.
As a program partner, Sky Engine aims to promote its offerings at NVIDIA and third-party events, as well as gain early access to various NVIDIA hardware and SDKs to further speed up deep-learning application development time and performance. Within an AI City environment, the Sky Engine AI platform can be used as a developers’ tool to create several smart city solutions for telecommunication, retail, law enforcement, security, electronic toll collection, parking operations, banking and insurance, logistics, traffic management and customer loyalty.
Dr Bartek Włodarczyk, PhD, Sky Engine’s CEO says, “Sky Engine joins NVIDIA’s Metropolis Partner Program to expand its thriving ecosystem further and boost its business and technology development. Together, we bring the advantage of our evolutionary Sky Engine AI deep learning platform to resolve the most fundamental problems in the AI-driven computer vision in smart cities.”
Learn more about SKY ENGINE AI offering
To get more information on synthetic data, tools, methods, technology check out the following resources:
- Telecommunication equipment AI-driven detection using drones
- A talk on Ray tracing for Deep Learning to generate synthetic data at GTC 2020 by Jakub Pietrzak, CTO SKY ENGINE AI (Free registration required)
- Example synthetic data videos generated in SKY ENGINE AI platform to accelerate AI models training
- Presentation on using synthetic data for building 5G network performance optimization platform
- Working example with code for synthetic data generation and AI models training for team-based sport analytics in SKY ENGINE AI platform