AI Comes to the Classroom

AI Comes to the Classroom

How AI and machine learning can help campuses keep the pace with the evolving learning environment

The biggest trend in video surveillance and indeed the security industry as a whole over the past several years has been the rise of artificial intelligence (AI) and the revolutionary promise it holds for the market. What once seemed like capabilities reserved only for the characters of science fiction novels and movies, are quickly becoming a reality because of advancements in computing combined with parallel breakthroughs in machine learning technology.

This has subsequently resulted in a renaissance for video analytics, which were frequently written off by systems integrators and end users as being an over-hyped solutions. Indeed, many of the vendors that offered video analytics as a standalone solution as little as a decade ago have now been largely relegated to the ash heap of industry history via company or patent acquisition. Now, however, the technology is once again flourishing with fresh venture capital funds flowing into an evergrowing number of companies. There are still many lingering questions about what tangible effect these advancements are going to have on the wider industry and especially in a vertical like education where users have to get every bit out of their investment dollar. Just because a Fortune 500 organization or large city can afford to spend millions on a state-of-the-art video surveillance system doesn’t mean that your average K-12 or college campus is going to see any real benefit from AI on a practical level right?

The fact is that schools—be they primary or secondary, public or private—have the same duty to protect students and staff members as a business would to protect their customers, stakeholders and workforce. That responsibility requires that schools look into cutting-edge technologies like AI, which stands poised to fundamentally alter the landscape of physical security.


The recent rash of school shootings across the country has shined a bright spotlight on issues surrounding campus security and the shortcomings of more traditional solutions have really been brought to the forefront. While more public schools today use video surveillance than at any other point in history, the fact is the vast majority of these camera networks are not actively monitored, which limits the role they can play in mitigating incidents. However, with the rise of AI, schools could get more out of their camera deployments as it would give them a better chance to have advance warning of a potential attack.

For example, take the shooting that occurred earlier this year at Marjory Stoneman Douglas High School in Parkland, Fla., which claimed the lives of 17 people and resulted in more than a dozen others being injured. The accused gunman, identified as a 19-year-old exstudent, had been expelled from the school prior to the massacre and his presence on campus was an immediate red flag. It’s not hard to see how an AI-powered solution could be used in the future to stop similar incidents from occurring given how the technology provides end users with the ability to more easily verify identities and even behaviors using video surveillance. Leveraging advanced facial recognition and/ or behavioral anomaly detection capabilities offered by AI, school administrators and security staff could be immediately notified when former students or disgruntled staff members or parents set foot on a campus and keep track of their movements across facilities.

Even for incidents involving individuals who have exhibited no prior warning signs, machine learning offers end users the capability to spot suspicious behaviors that could be an indicator of a potential attack. Say, for instance, a campus has a clear backpack or even a no backpack policy and someone shows up carrying a duffle bag or rifle case, AI-powered surveillance software would be able to quickly determine that such behavior is abnormal for the campus and alert the proper authorities. Once AI software has been given an opportunity to study a dataset over a period of time, it can easily identify when an anomaly occurs.

Another benefit of deploying AI in schools is that it provides returnon- investment beyond security, which is something that has proved elusive for much of the rest of the industry.


Although the primary application of AI and machine-learning solutions today is to bolster the effectiveness of video surveillance systems and those tasked with monitoring them, the use cases for this technology continue to evolve. Among these include robotics in the form of unmanned ground vehicles (UGVs), unmanned aerial vehicles (UAVs), more commonly referred to as drones, and various standalone solutions, such as stationary towers.

Robotics are not only a cost-effective force multiplier given their relatively low deployment costs compared to human guards and police officers, but they can also serve a multitude of purposes beyond just video surveillance. Imagine, for typical day-to-day operations, having a tower outfitted with a number of megapixel cameras and/or high resolution touchscreen monitor that could serve as an emergency communications station and also provide a variety of information, such as bus routes and campus maps. During an actual emergency or when the school is closed, however, the tower could serve as an extension of the video surveillance system and leverage AI to identify people, vehicles, etc.

The same also holds true for UGVs and UAVs. Whereas in the past human operators would be needed to analyze and make decisions based on the information collected via video and other security sensors, robots with built-in AI capabilities can now process data and make determinations about what is and what is not a security risk on their own and thereby reduce the demand on human capital. In the wake of the shootings at Parkland and Santa Fe, Texas, there has been a push among lawmakers across the nation to increase the number of police officers and security personnel patrolling the halls and campuses of K-12 schools, but having additional manpower is an expensive proposition and much more so over the long-term when compared to using AI-powered unmanned vehicles.


The uses of AI also do not have to just be limited to security within the education market but could be expanded upon to become a solution to improve the overall learning environment. In schools where cameras have been placed in the classroom to ensure appropriate behavior from students and faculty, AI is already being leveraged to help improve teacher development.

Rather than have a person serve as an intrusive classroom observer, surveillance footage can be utilized to help staff see what teaching strategies and methodologies are the most effective for their students. Some may argue that having video cameras in classrooms creates an uncomfortable environment and is invasive but it doesn’t have to be viewed as a tool of “Big Brother.” Rather, it should be seen as an opportunity to keep students and teachers safe, while also serving to help teaches strive for excellence.

AI and machine learning are undoubtedly going to be a critical part of video surveillance moving forward and it’s incumbent upon schools to learn how they can take advantage of it to improve safety and boost the effectiveness of teachers and educational experiences of students.

This article originally appeared in the October 2018 issue of Campus Security Today.