Dr. Zheng (Thomas) Tang

Dr. Zheng (Thomas) Tang

Senior Deep Learning Engineer at NVIDIA, expert in computer vision and machine learning

Taiwan’s Electronics Leaders Advance Industrial Automation With NVIDIA Metropolis and NIM

1 minute read

Published:

I’m excited to share that leading Taiwanese electronics manufacturers—Foxconn, Pegatron, and Wistron—are leveraging NVIDIA’s Metropolis platform and NIM microservices to transform industrial automation. This development was highlighted during NVIDIA CEO Jensen Huang’s keynote at COMPUTEX 2024.

Foxconn and its subsidiary, Ingrasys, are utilizing NVIDIA Omniverse and Metropolis to create digital twins of their factories. These virtual replicas enable efficient planning and enhancements in worker safety across multiple manufacturing sites. At COMPUTEX, Foxconn showcased how digital twins assist in optimizing the placement of video cameras within factories to capture critical data insights.

Pegatron, operating over 20 million square feet of factory space and managing more than 15 million assemblies monthly, has adopted NVIDIA NIM and Metropolis multi-camera tracking reference workflows. This integration aims to bolster worker safety and productivity on production lines by merging digital twins in Omniverse with Metropolis’s real-time AI capabilities, facilitating improved monitoring and operational optimization.

Linker Vision, a specialist in AI vision insights, is deploying NVIDIA NIM to assist factories in implementing AI agents capable of responding to natural language queries. Utilizing the NVIDIA Visual Insight Agent (VIA), these systems continuously monitor video feeds of factory floors. Operators can prompt these AI agents with natural language questions and receive immediate, context-aware responses, enhancing operational efficiency and safety measures.

The integration of NVIDIA’s Metropolis platform and NIM microservices signifies a pivotal shift towards AI-driven industrial automation, promising substantial improvements in efficiency, safety, and product quality within the manufacturing sector.

Taiwan Electronics Leaders Automation

You May Also Enjoy

Releasing the Physical AI Smart Spaces Dataset for AI City Challenge 2024 & 2025

1 minute read

Published:

Excited to announce the release of the Physical AI Smart Spaces dataset—developed as part of NVIDIA’s Open Physical AI Dataset initiative and featured at NVIDIA GTC 2025. This large-scale multi-camera 3D perception dataset supports AI City Challenge Tracks for 2024 and 2025, advancing research in multi-target multi-camera tracking, 4D occupancy, and digital twin applications.

Metropolis Spatial AI Powers Mega Omniverse Blueprint Featured at CES 2025

1 minute read

Published:

Excited to share that our work on Metropolis Spatial AI was showcased in the CES’25 Keynote by NVIDIA CEO Jensen Huang as part of the Mega Omniverse Blueprint—an end-to-end framework for simulating and deploying intelligent robot fleets. This milestone highlights the critical role of multi-camera tracking and real-time location systems in the future of industrial automation, smart factories, and digital twins.

Announcing the Official Release of the Metropolis Multi-Camera Tracking AI Workflow

2 minute read

Published:

Announcing the official release of the Metropolis Multi-Camera Tracking AI Workflow, featured in NVIDIA GTC’24 Keynote by Jensen Huang. This innovative solution accelerates the development of vision AI applications for large spaces, enhancing safety, efficiency, and management across various industries. Leveraging NVIDIA’s cutting-edge tools, this workflow offers a validated path to production, customizable AI models, and comprehensive support, enabling seamless development from simulation to deployment. Join us in transforming infrastructure and operations with advanced AI technology.

Advancing AI with NVIDIA Omniverse at CVPR 2024: AI City Challenge Highlights

2 minute read

Published:

As the lead organizer of the AI City Challenge at CVPR, I’m excited to highlight our progress with NVIDIA Omniverse, which provided the largest indoor synthetic dataset for over 700 teams from nearly 50 countries. This dataset, essential for developing AI models to improve efficiency in retail, warehouse management, and traffic systems, included 212 hours of video across 90 virtual environments. Our global collaboration with ten prestigious institutions underscores the effort to advance AI for smart cities and automation. NVIDIA’s innovations, like Omniverse Cloud Sensor RTX, will further accelerate autonomous system development. Join the Omniverse community to stay updated and connected.