blue-dots-3

Case Study

Contractors in the construction industry

Contractors in the construction industry

A typical implementation starts with training workshops on the used methodology. Based on this, the User Interphase and final implementation will be modelled. 

After these initial workshops, the actual technical training will be done. The installation, configuration and use of the technology will be explained, followed by the first installation in a testing environment. 

Finally, taking all the user comments into account, a final production environment will be created for all future installations.

Video and Sound
Streaming Solutions

Room40 has partnered with Nokia to deliver a state of the art scalable real time Video-and Sound Streaming solution. 
As an example the following real life situations are currently identified. In collaboration with future users other solutions can be implemented using adaptations on the existing applications.

workshop summary
  • Workshop 1
    • Kickoff & situational awarenes
  • Workshop 2
    • Introduction OODA-loop
  • Workshop 3, 4 en 5
    • Technical sessions (video, sound and text)
  • Workshop 6
    • Testing environment and provisional acceptance
  • Workshop 7
    • Production environment and final acceptance

Document and
Text Streaming solutions

Room 40 has partnered with Intuview to deliver a state of the art
text analysis solution using Artificial intuition

The core of the technology is a patented (in the US and Israel) method for integrating statistical algorithms with ontological based input, to imitate processes of human-reading of texts.
The combined knowledge of seasoned subject matter experts regarding texts of the same domain used in training; are applied to the processed texts through algorithms. This method is called “Artificial Intuition”. 

A human reaches “intuitive” conclusions – even by superficial reading – regarding the authorship and intent of a given text, subconsciously deriving them from previous experiences with similar texts or from linguistic knowledge relevant to the text. Then as the human accumulates more information through other features (statements, spelling, and references) in the text, he either strengthens his confidence in the initial interpretation or changes it. 

Fencing algorithms
 Object classification

Detect cars and trucks entering and leaving the site.

Tripwire algorithms 
Object classification

Count vehicles or people crossing a line or area thus enabling realtime reporting  on number of workers and machines at a location.

Anomaly detection
 People filtering

Detect a group of people assembling in a scene for a specified period of time.

Video Analytics 
Anomaly detection
  • Detect panic (crowd runs in multiple directions) by means or direction anomaly
  • Detect a sudden explosion by means of density anomaly
  • Detect obstacles by means of a dwell anomaly
  • Detect fast drivers in traffic situations by means of a velocity anomaly

  • Detect cars taking a wrong way or turn in traffic situations by means of direction anomaly

Fencing algorithms Object classification

Detect if workers are wearing their safety gear such as helmets

Other situations such as detection of oversized vehicles, stalled car, debris or animals on the roadway and measuring traffic density are also possible.

Video Analytics 
Anomaly detection
  • Detect and localise machinery that is in operations
  • Detect and localise someone breaking in a car/truck’s window to generate an alert
  • Detect aggressive behaviour to generate an alert

Other situations allowing for a stand alone sound solution to generate events and anomalies are also possible. Specific automated sound recognition can be provided when sufficient sound examples are available for the machine learning algorithms.

Using text algorithms to perform automatic tagging on all site related documents (reports, mails, etc…) allowing for more efficiency in document control and ultimately having an automated system in place for risk and claim management.

Using social media text streams to detect the sentiment of the surrounding inhabitants towards the site construction works in a specific region, thus enabling better performance statistics regarding nuisance towards the environment.

Integration of the sound analytic algorithms into the Room40/Nokia solution for a unified UI and intuitive incorporation of technologies.

Using video analytics and open ANPR software to recognise license plates.

Further enhancement of the video object classification to detect specific machinery at the site. This can be done through machine learning or even by detecting logo’s or other specific criteria such as QR codes.

Further enhancement of the sound object classification to detect specific site related sounds such as falling objects etc…

Event generation through analysis of social media text streams and integration of events into Room40/Nokia solution.