Sightcorp logo

AI solutions for Covid

Comply with C-19 regulations

Live occupancy monitoring system

Live face mask detection, spoof proof

Face recognition & temperature detection

Audience analytics


AI re-opening solutions for COVID-19

With stores and business reopening we have ready to use solutions that can work together with existing or new hardware at any premise and are adaptable to any changes in regulations.


Kiosk Access control Face recognition/ Fever detection

Use Cases

Retail and Supermarkets

Automatically control and limit the number of customers within a store with our sensors to ensure keeping your customers and employees safe. Designed to work perfectly in stores with single or multiple entrances. Learn more about our occupancy monitoring system here


Offices and Workplaces

Access to workplaces and buildings has changed since the spread of the virus and technology can be great tool for keeping everyone safe once they start coming back to the shared office spaces.


Airports and the aviation business need to reassure customers that safety regulations are implemented and followed to make sure their travel is as safe as possible.

restaurant bars and clubs

Restaurants, Bars and Clubs

With nightlife and restaurants reopening it is crucial to follow guidelines set by the government and informing customers of the precautionary safety measures taken.

What is a Smart Store Traffic Light System?

Our Smart Store Traffic Light System is comprised of deep learning technology, face detection algorithms, IP or CCTV systems, and digital signage to create a comprehensive solution to the changing dynamics of retail resulting from Covid-19. Our out of the box technology works by anonymously counting the number of people entering a building. Once capacity has been reached an alert will be clearly displayed via digital display in a traffic light ‘stop and go’ ‘red and green’ format. As an additional feature setting, the technology can also simultaneously detect if an individual is wearing a mask upon arrival to the store (depending on store location and local policies). Again displaying information on whether it is ok to enter the premises. This real-time, up-to-date information ensures effective store updates, communication, and message transparency for its customers.  

How does occupancy counting work?

 Occupancy counting works by using sensors and computer vision technologies together to accurately count footfall entering and exiting a building. These sensors capture live occupancy data and present this data through clear visual warnings on digital displays. These displays can be placed at the entrance of a building and  when occupancy limits are met, visitors are notified in real-time. Alternatively, a text message or email alert can be sent to building security or administrator to make them aware of people entering without authorization. The technology is easy to use and can be rapidly deployed, meaning a safe environment for all with no delays or time consuming installations. Our occupancy counting system is also discreet and anonymous, ensuring privacy regulations are adhered to at all times and that the products are not intrusive for the public.


What is thermal detection?

Thermal detection or imaging is the action of converting infrared radiation, also known as heat radiation, into visible images that depict the distribution of temperatures in an area viewed by a thermal camera. Using AI technologies, such as deep learning, computer vision and face detection algorithms, alongside cameras, elevated facial temperatures can be detected in members of the public in order to highlight potentially sick or Infectious individuals.  The technology is being implemented in places such as hospitals, college campuses and Airports as part of the access control process.


Thermal detection camera

Using a combination of deep learning machines and forward-looking infrared cameras (FLIR) an optimized public screening system can be set up. The specialized cameras have thermal and visible sensors that allow for elevated temperatures to be picked up in public areas. Using AI this can then be recognized and communicated back to the public in the form of an alert. If someone is detected to have a temperature, an alert can be sounded using an actual alarm, flashing light, or messaging format to make the individual themselves or a member security aware. This temperature screening system is especially useful in Airports in helping to manage and minimize the risks associated with the global pandemic.  

Occupancy counting and privacy

All the data collected and analyzed by our face analysis system used in the process of occupancy counting is completely anonymous. This anonymized data is transmitted and stored in an encrypted format (zeros and ones), to ensure that data privacy rights are always upheld and in line with GDPR regulations. Our software has been created by our team of in-house software engineers where products are built with privacy by design.


Contactless Access Control

Secure buildings such as corporate businesses and government buildings have incorporated dual biometrics (Facial recognition and fingerprint) for ID confirmation and access control into their buildings over the last few years. Given the new contactless environment that is required as a result of Covid 19, facial recognition is appearing as the more sanitary solution to its touch-initiated counterpart. New liveness detection features have been incorporated in our facial recognition product DeepSight which provides extra security against spoofing attacks and unauthorized individuals from entering secure premises. Additional to this, thermal sensors can be used to detect if individuals entering have a temperature and can deny access as a result. 



What type of buildings can DeepSight be installed in to monitor occupancy?

Our occupancy monitoring system can be implemented and installed in any type of building to keep track of footfall and capacity limits.The product is easily integrated and discrete, which therefore makes it practical for any setting. Due to the Covid-19 crisis, our team has designed our crowd analysis system around buildings reopening safely and responsibly with privacy at the forefront of our product design.

Does Sightcorp handle the installation?

No. Our product has been designed with ease of integration in mind, meaning that it is simple to install with no in-depth technical knowledge required to operate it. The product also comes with easy to follow instructions which acts as a useful reference guide.

Can DeepSight Occupancy monitoring identify individuals?

No. Information pertaining to individual identity is never gathered or stored. Instead, data is collected anonymously and in an encrypted format.

Can I monitor queues outside of my premises?

No. The occupancy monitoring system has been designed only to capture footfall inside of the building.

What are the benefits of occupancy counting?

Occupancy counting has long-term benefits that will extend past its use as a safety tool during covid-19. Footfall monitoring provides useful insights into how spaces are being used and help to potentially reduce unnecessary rental costs. Additionally, crowd analysis software can be used to identify peak hours for retail businesses, helping them to create better staffing plans in accordance with peak hours and shop demands.

Where is the best place to position display screens?

The design of your building comes into play when it comes to selecting where the best place is to position your digital screens. In most cases, building entrances seem to be the prime location as they can accurately monitor traffic coming into the building and ensures that people can clearly see occupancy updates as they approach and don’t know if it is ok to enter.

Ready to learn more?

Technical Specifications

The table below shows how FaceMatch SDK performs on the Labelled Faces in the Wild (LFW) dataset:

FPRTPRThreshold (Inverse of distance)
0.10.99900 ±0.002130.55448
0.010.99667 ±0.005370.59791
0.0010.99367 ±0.006050.62989

FPR = False Positive Rate
TPR = True Positive Rate

These results are an indication only and are based on the specific dataset Labelled Faces in the Wild. Customers can expect similar performance, with possible variations due to hardware and the availability of annotated data.