Inability to monitor all activities in a large area
Sequence Number
4
Industry
Seaports
Banner
How 5G enabled
Wider coverage with AI’s ability to automatically detect authorised personnel and vehicles while monitoring activity, triggering alarms or alerts when necessary.
Data Flows
Title
Devices
Icon
Description
Sensors (cameras) located at multiple locations across the site: fixed/drones/robotics/cars/staff/etc.
Timeseries data to support camera images
Title
Connectivity
Icon
Description
Time series data transport
Camera images
Asset data (maintenance records) access
Title
Edge Compute
Icon
Description
Several activities are in real-time
Camera – MV interpretation
Title
Cloud Compute & Storage
Icon
Description
All data collected from assets (both historical and real-time)
Enterprise-owned storage
Title
Applications & Services
Icon
Description
Non-time critical activities
MV and some ML focus; E2E automated
Multiple MV models linked to apps
Title
Inform Decision Makers
Icon
Description
Errors and safety violations reported immediately to the operations centre of the site
Title
Support Decision Making
Icon
Description
End of process
Application Logic
Description
Camera-fitted drones would be a key enabler given the size of the area to be monitored.
5G enables this implementation to be real-time where images are captured and sent to the edge storage and compute while flying.
Edge computing with MV will immediately analyse images and perform required actions, e.g., makes a direct call, steer drone to an area, trigger an alert, etc.
Edge + 5G to be used for all time critical events.
Description
All edge-collected data will be stored long-term in Enterprise storage.
Focus on MV to spot the data needed for the different scenarios.
Development of the ML model is done through an iterative process. A quality ML model (fully data-driven) will require multiple steps to detect anomalies and potential failures.
Models will be stored and maintained by AI applications.
SMEs and data scientists to develop these models.
Description
The process from data collection to execution of models is fully automated.
MV models developed to support all application cases; MV model needed for each application case.
Various options for visualisation of entire operations (e.g., XR options on OpenXR platform).
Expected benefits
Reduced time and resources for safety surveys by physical workforce
Consistent and standardised monitoring by drones
Images captured can be processed for future planning
Key value created
Early detection of abnormal operations reduces risk of incidents and improves productivity