Page 26 - Security Today, March/April 2024

“In 2024 and beyond, it does not take a tremendous amount of foresight
to predict that AI will grow in use in almost every surveillance application across a range of markets.”
that Hanwha’s AI cameras can comprehend. We have heard from our customers that they require unique solutions to address their specific business challenges. This often involves the need to train custom objects not included in off-the-shelf AI cameras. FLEX AI is a cloud-based application that allows users to train objects with as few as 20 images.
AI DRIVING NEW EFFICIENCIES
The continued integration of AI and Machine Learning in secu- rity and surveillance systems has enabled smart video analytics, automated threat detection and predictive analysis.
Depending on the environment and activity in surrounding ar- eas, an organization may need to consider the factor of “unnec- essary information” when it comes to AI analytics to detect and track motion. A security team only needs to know if something comes over the perimeter or enters the grounds, but the elements on the outside usually are not that useful. For example, if there are many waving trees along a perimeter or surrounding a build- ing, then those environmental factors may trigger false alarms.
Combining AI into video surveillance systems leads to fewer false alarms and more effective and accurate forensic searches ef- fectiveness. AI also enhances bandwidth reduction algorithms as we see a heightened need for more accurate AI-based detection of people, objects and vehicles. Previously technologies focused on pixel changes created by any type of motion: rain, snow or video noise, which could cause video bandwidth to increase. Now, all these pixel changes are ignored to focus only on what users need to see. AI is also effective to reduce video noise and motion blur.
Heavily wooded areas versus open areas could also be factors in determining context. Often, security teams do not care much about trees swaying in the wind since they are more focused on the fence line or only want to see people walking inside the pe- rimeter.
AI-based “’smart” compression and noise reduction technolo- gies are growing in use. They can say to a user “Here’s this high- resolution camera footage, do you want to reduce bandwidth and manipulate the compression based on the objects we care about?”
This level of context awareness takes AI beyond the level of pre-configured algorithms. It lets a system gather information about its environment and adapt its behavior accordingly. Now, the camera is making choices to optimize its performance based on what it has learned in the past and what is important to the user.
The coming months should also see a rise in the use of AI across many vertical sectors,
Schools. Digital imaging surveillance technology combining
AI with on-board audio and video analytics can help school administrators get a better handle on access control and monitoring of hallways, classrooms and exterior parking lots. For example, knowing which doors visitors can access and exit the building is important when placing cameras. These analytics deliver actionable data that can drive intelligent monitoring for education facilities, helping administrators get a better handle on access control and monitoring of hallways, classrooms and exterior parking lots.
Healthcare. The use of AI is spreading across the healthcare industry to enhance patient care, improve operational efficiency and even contribute to medical research. From a security and sur- veillance perspective, hospitals are complementing their cameras’ security monitoring performance with enhanced data-gathering capabilities combining intelligent audio/video analytics and AI.
With so many feeds to monitor across the different areas of a hospital, putting a security person in front of a video wall is not practical since an individual is realistically only able to monitor 10 to 20 cameras at a time. Hospitals are using AI combined with video analytics to help manage their networks of cameras and devices, shifting their security and surveillance approach from reactive to proactive. The result is targeted object detection and classification, which can save time for hospital security teams by speeding forensic searches. When an incident occurs, locating a person of interest can take a matter of minutes instead of having to spend hours sifting through hundreds of camera streams.
AI also is playing a larger role in cameras used for license plate recognition, recording vehicle entry and exit, and alerting staff to potentially dangerous activities in real-time.
Retail. New AI technology has added the power to do people- counting, body temperature detection, object detection, license plate recognition, behavioral observations and any number of actionable business functions. These new video solutions are ad- dressing the industry’s need for scalable and cost-effective surveil- lance solutions that can help organizations monitor their stores and detect suspicious activity, preventing theft.
Over the years, we have seen a growing shift in the retail in- dustry away from traditional on-prem servers and NVRs towards cloud-based solutions. Retailers can now deploy self-contained systems while fully realizing the potential of edge storage, multi- camera recording, remote access and on-prem security system management. It is important for retailers to easily customize and grow their surveillance systems based on their specific needs.
Intelligent video surveillance and AI technology also helps re- tailers be proactive when it comes to in-store shrinkage.
With security and surveillance devices now increasingly be- ing tasked to do more than just “monitor and protect,” compre- hensive, AI-powered intelligent technologies
are now regarded as 360-degree, total business
transformation solutions.
Aaron Saks is the senior technical marketing and training manager at Hanwha Vision America.
26
MARCH/APRIL 2024 | SECURITY TODAY
ARTIFICIAL INTELLIGENCE