CENTRAL EVENT DATA INTELLIGENCE CORE
In AIoT and smart city environments, the true value of data is not merely in collection,
but in identifying events in real time, understanding anomalies, driving decisions, and automating workflows.
DFS (Data Fusion Service) is the core event data middleware within the ViDAware architecture,
designed for highly complex environments involving multi-source communication and video data.
Video, sensor, and communication data enter the event bus in real time
DFS Data Fusion Service
Integrates industrial and environmental sensors, supports communication protocols such as Modbus and TCP/IP, receives temperature, humidity, water level, pressure, and other sensor data in real time, and standardizes the data for downstream use.
Connects existing third-party systems through SQL/API interfaces and integrates structured data such as access control, lanes, billing, and equipment ledgers. This prevents data silos and allows historical records and real-time data to operate together.
Overlays real-time sensor data and AI analytics on video feeds, such as people counts, event status, and environmental indicators, providing intuitive and visualized evidence for real-time monitoring and decision-making.
When sensor values or video analytics trigger abnormal conditions, such as excessive water levels or smoke detection, the system generates alerts in real time and automatically associates the corresponding video events and records to accelerate notification, response, and audit workflows.
Integrates sensor data, video streams, and AI analytics into real-world scenarios, including smart cities, smart factories, traffic monitoring, and campus management. It supports cross-system collaboration to improve operational efficiency and decision quality.
Reviews historical events, trends, and statistical indicators through dashboards to support equipment status analysis, risk prediction, and operational reviews, turning real-time data into a long-term decision foundation.
VIDA.ai serves as the core data hub, integrating front-end sensing devices and video streams. Through real-time AI analytics and data processing, it turns multi-source data into visual indicators and decision evidence, supporting intelligent operations and management across systems and sites.
Aggregates video streams and various sensor data. It supports RTSP and H.264/H.265 video sources, as well as industrial and system communication protocols such as TCP/IP, Modbus, and HTTP/XML, creating a standardized real-time data entry point.
Uses AI models and rule engines to process environmental monitoring data (PM2.5, rainfall, water level), safety events (smoke, flame), and traffic status in real time, transforming raw data into interpretable, decision-ready information.
Outputs analytics results and event information to management systems. It supports TCP/IP, Modbus, HTTP/XML, and other integration methods, and generates JPEG event snapshots and MP4 video records for subsequent management, auditing, and decision-making.
Integrates rainfall, water level, PM2.5, and AI video recognition to enable real-time disaster warning and dynamic traffic management, helping city agencies respond quickly and optimize traffic decisions.
Uses Modbus and AI video analytics to monitor equipment operating status and personnel safety, while integrating access control and production systems to create a visualized smart manufacturing environment.
Quickly understand the outstanding performance of radar wave water level sensors through real-world site footage and key technical features.
Detects water levels remotely without being affected by turbidity, sediment buildup, or floating debris on the water surface.
Uses advanced microwave technology to deliver millimeter-level precision data for professional hydrological monitoring requirements.
Significantly reduces the frequency of manual cleaning and recalibration, making it suitable for stable long-term outdoor operation.
Supports 4G / NB-IoT technologies for real-time monitoring data upload to the cloud platform.
Can be paired with solar power for independent operation, enabling field deployment without complex cabling or network wiring.
Installed above the water surface with a robust structure, reducing the risk of equipment being washed away or damaged during heavy rain and flooding.
From urban safety and environmental monitoring to manufacturing AOI inspection and smart factory access/environment control, industrial-grade AI video recognition hosts integrate Edge, CMS, and DFS architectures to build city- and industry-grade AI vision applications that are long-running, scalable, and governable.
This video only supports YouTube playback
Due to restrictions set by the original channel, please watch the full content on YouTube
Watch on YouTube