Real-time Analytics
Kaohsiung needed citywide situational awareness across transportation, flooding, disaster response, and public-safety workflows, but departmental silos and traditional computer vision left agencies unable to interpret abnormal events or share information quickly enough.
Reported impact
Kaohsiung’s vision AI platform reduced development effort by 85 percent, cut response times by up to 80 percent, enabled richer incident reports, and now supports city-scale coordination across transportation, water management, healthcare, logistics, and more than 300 urban scenarios through a unified video-intelligence layer.
Linker Vision built Kaohsiung’s smart-city platform on NVIDIA’s three-computer strategy so video AI could move from isolated detections to city-scale operational intelligence. The deployment starts by converting satellite and aerial imagery into OpenUSD scenes and running a city digital twin on NVIDIA Omniverse and NVIDIA OVX servers. NVIDIA Cosmos generates synthetic video for hard-to-capture scenarios such as flooding or infrastructure damage, while NVIDIA NeMo Curator and nv-grounding-dino help curate and label real and synthetic data for VLM fine-tuning. At runtime, NVIDIA Metropolis Blueprint for Video Search and Summarization combines vision pipelines and Cosmos VLMs on NVIDIA DGX servers so AI agents can analyze thousands of live camera feeds, describe incidents, alert agencies and citizens, and feed those outputs back into an interactive command center. That architecture lets Kaohsiung coordinate cross-department responses in real time instead of relying on isolated municipal systems.
City camera streams feed VSS-based AI agents, VLMs interpret traffic, flooding, and safety events, alerts and summaries are sent to the relevant agencies and citizens, and the outputs are visualized inside an Omniverse-based digital twin command center for coordinated response.
It uses the NVIDIA VSS Blueprint to build video analytics AI agents that can process thousands of live camera streams around the city and deliver deeper insights into traffic incidents.
Linker Vision is integrating 30,000 diverse smart city camera streams, all managed in a city-scale 3D digital twin platform.
Reduced development efforts by 85% using the VSS blueprint to build visual AI agents.
Reduced response times by up to 80%, enabling emergency services to reach sites faster.
The system is trained to understand more than ten major urban and enterprise domains ... and 300+ scenarios such as traffic accidents, disaster response, public safety, and infrastructure management.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
NVIDIA Sample Oct 9, 2026 California Department of Transportation (Caltrans) Caltrans needed to inspect and monitor roughly 1,200 active transportation projects more frequently and safely, but manual site visits were slow, inconsistent, and risky for staff working around traffic, bridges, and… Remote operations up to 100 miles Esri ArcGIS · NVIDIA CUDA · NVIDIA Jetson Orin NVIDIA Sample Mar 4, 2026 Israel Meteorological Service The Israel Meteorological Service needed to produce faster and more localized weather forecasts for floods, fire seasons, and other severe conditions, but conventional numerical weather prediction required large CPU… 2.5-kilometer resolution forecasts NVIDIA Earth-2 · NVIDIA Earth-2 Corrector Diffusion (CorrDiff) · NVIDIA PhysicsNeMo NVIDIA Sample Archived · Jan 28, 2026 City of Raleigh Raleigh needed to improve congestion management, mobility, and street safety as the city grew, but manual traffic counts and disconnected sensor repositories made it hard to visualize conditions, respond to incidents… $9.7 million annually in time and fuel costs Esri ArcGIS · Microsoft Azure · NVIDIA Blueprint for video search and summarization (VSS) 