Cyrus Innovations

+65 6747 1515


Vi Dimensions

We Discover. Going Beyond Detection.

Vi Dimensions was founded in 2015 with the simple idea that video analytics can be done in a much better and efficient way with the ultimate goal to revolutionize safe city surveillance harnessing thousands of cameras.
The company uses its patented algorithms and proprietary unsupervised Machine Learning techniques to derive meaningful information and actionable insights from live streaming video data. This translates to immediate value to the customer not only in terms of security and surveillance but also improves the organisation’s safety, operational and maintenance aspects.
Our advanced and innovative system analyses vast amounts of real-time streaming (or archived) data autonomously for abnormal behavior and events. It does not require human intervention to automatically discover dominant motion patterns which means that unlike conventional systems, it does not require a human to specify rules necessary for detection.


Abnormality Detection Technology


Key Product Features:
Identify patterns – System is able to automatically identify patterns (i.e. motion, trajectories) of people, vehicles and objects in scenes.
Discover deviant patterns and behaviours – System is able to find deviations and abnormalities to warn of potential threats (especially those not known beforehand).
Fast and autonomous – It is able to do it fast and autonomously searching through vast amounts of constantly streaming (or archived) video from thousands of cameras using GPU.
Not limited by prior human knowledge – Discovery of abnormal events is not limited by prior human knowledge because the system is intelligent enough to self-learn and adapt to different and continuously changing scenarios.
User feedback – However, the system is able to take in prior human knowledge if necessary. It will speed up the learning for the obvious parts that can be easily accounted for by humans
– As abnormalities are subjective, this introduces practical tuning according to the circumstance or operator requirements.
Integration with existing systems – We can easily add onto customers’ existing video analytic systems and video management systems so they can increase coverage of their cameras.
Top 10 search – System is able to list the top 10 most abnormal events based on camera or geographical locations so that users can just focus on these events.
Pro-active approach – Abnormal events discovered may surface safety, security, operations and/or maintenance implications which could lead to more pro-active follow-up actions depending on its impact on the user and the organization.

Solution Architecture


Solution Architecture

Key User Benefits


Massive manpower savings – Human operators are not needed to eyeball and monitor the thousands of cameras for events.
Improved flexibility and capability – Users need not define rules as the system can self-learn and detect abnormalities.
Improved efficiency – Users can be more proactive and not reactive since the system can notify the user ahead of time to potential threats based on abnormal events and occurrences he was not actively looking for.
Increased surveillance coverage – Previously only about 10% of cameras deployed can use rule-based analytics. Our technology can increase this to 100% coverage.