Surveillance Video Processing

PROBLEM • Gaining a competitive edge in real estate with AI-driven geospatial analytics with Data & knowledge as a business power. • It is not a secret that data analysis can significantly improve decision-making in real estate. How to predict and infer space occupancy and utili...
Featured story Blog
Surveillance Video Processing

PROBLEM

• Gaining a competitive edge in real estate with AI-driven geospatial analytics with Data & knowledge as a business power.
• It is not a secret that data analysis can significantly improve decision-making in real estate. How to predict and infer space occupancy and utilization to optimize the use of commercial and corporate spaces?
• Knowing how people behave and where they are located gives many businesses a competitive advantage. A good example could be increasing the number of employees in case of the high frequency of customers in some period of the day (e.g., bars, hotel’s reception)
• Real-time analytics and AI can provide valuable insight into indoor movement
and positioning and how space is occupied and utilized. Analyze surveillance videos and make outputs for the BI tool.

SOLUTION

• The process:
We defined which parts of the system can be generic and camera-specific and need to be adapted to each case.
• The pilot project includes retraining networks that are camera specific, representing what networks see via data that is easy to be manipulated. Then, we use this data post-processing to meet our client’s specific needs.
• SmartCat uses the database for training multiple models designed to extract different kinds of information from videos.
• We perform an automatic secondary analysis of the collected raw data, so it can be used to create human-readable insights, alerting, and visualizations. As a result, Analytics about how many persons enter the space, how long they stay in each position, and which resources they use serve as business intelligence for clients to make smart decisions.

RESULTS

SmartCat collects relevant data from videos with high accuracy. Up to 90% of people and objects were successfully detected. This data is then automatically manipulated and transformed to accommodate specific client’s needs.

SmartCat improves the systems that support the algorithms applicable to fisheye cameras.

For more information, you can contact us here: info@smartcat.io