SAFR shares its forecast for the physical security industry in 2022

SAFR from RealNetworks, a facial recognition platform for live video, shared its top predictions for the physical security industry in 2022. These include dropping fears about AI, adoption hybrid cloud solutions and pandemic use cases.

Better conversations around AI

Today’s conversations about AI are often based on fear. Media coverage has been dominated by depictions of rampant prejudice and invasions of privacy. While these are legitimate concerns, letting our fears dictate the conversation may prevent us from reaping the potential benefits, according to SAFR. The trend for 2022 will be to move away from this fear and towards a more balanced outlook and a better understanding of the challenges and opportunities of this emerging technology.

This does not mean taking a stance of false complacency where we accept AI as a panacea that will solve all of our problems. Rather, engineers and product designers must remain vigilant about privacy and biases and create solutions that mitigate risk.

When it comes to bias, for example, we need to be wary of how it can infect AI models and how historical bias in the ground truth of a data set can be magnified by an algorithm. . SAFR is very active in this area and recently funded a research program at the University of Washington to explore biases and develop policy recommendations.

To the edge

For compute-intensive computer vision applications, it has become increasingly clear that it is not possible to perform this processing only in the cloud. Downloading thousands of hours of raw video is a poor use of cloud resources and bandwidth. On the other hand, processing the raw pixels at the edge, even before they are compressed, is more precise, efficient and secure. Moving all business operations to the cloud can also create single points of failure that could be catastrophic for organizations. But the solution isn’t to ditch the cloud and get back to working on-premises. Instead, SAFR predicts that 2022 will see the creation of more hybrid solutions where much of the processing is done at the edge, while the cloud remains responsible for coordinating and orchestrating massively distributed computer vision applications. .

One of the advancements that are helping us move in this direction is that video cameras are getting smarter and smarter. In fact, they’re so smart that the entire SAFR stack can now be ported to System on a Chip (SoC) processors that power some of the best cameras in the world.

With a hybrid solution, events are coordinated in the cloud while video is processed at the edge. This is more scalable in terms of cost, as organizations don’t have to pay to move data from cameras to the cloud for processing and then return it to the organization for review. It also increases data privacy, as facial or biometric data does not leave the camera or is sent over the network. And, because the analysis uses the raw pixels directly from the camera instead of pixels that have been compressed, encoded and decoded, the results are also more accurate.

Learn from pandemic use cases

While the COVID-19 pandemic is not over, we have certainly learned from our experience helping organizations fight the virus and keep people safe. In 2022, the security industry will focus on developing contactless security solutions to minimize our reliance on physical credentials and to replace common surfaces such as fingerprint scanning at airports, according to SAFR. These non-contact solutions will lessen the spread of the virus by reducing in-person interactions as well as the number of surfaces people touch.

A good example is a hotel using a contactless application for video analysis. Here, guests enrolled in the hotel’s VIP program are first recognized by video cameras in the hotel lobby as they enter. Once customers are identified, the system automatically sends a notification to their phone that associates them with their reservation and provides them with their room number. This means that guests do not have to queue at the check-in counter or come into direct contact with hotel staff. Once in their room, guests can unlock their door using facial recognition or a QR code that has been sent to their phone as part of the automated check-in process.

Leave a Comment

Your email address will not be published. Required fields are marked *