AiMS —The New VMS Powered by AI to Prevent Museum Theft with Video Analytics
Musée du Louvre, also known as the Louvre, is one of the most visited museums in the world with the best security protection; however, there have still been several high-profile heists at the Louvre unavoidably.
Earlier this year, the Louvre recovered armor pieces stolen nearly 40 years ago. At the end of May 1983, two pieces of Italian Renaissance armor went missing: a showcase was broken into and the 16th-century Italian armors were taken away in one of the most mysterious heists in the museum’s history.
The most famous theft of the Louvre occurred during the summer of 1911 when three museum handymen stole the Mona Lisa. Before its theft, the “Mona Lisa” was not widely known outside the art world. Leonardo da Vinci painted it in 1507, but it wasn’t until the 1860s that critics began to hail it as a masterwork of Renaissance painting.
The ringleader of the theft, Vincenzo Peruggia, was arrested two years later while trying to sell the painting in Florence, Italy, and the painting was returned to the museum. The internal thief described snatching Mona Lisa from the wall and slipping it under his blouse. “It was all done in a few seconds,” Peruggia said.
Another high-profile theft took place in 1976 when three burglars broke into the Louvre at dawn and stole a 19th-century diamond-studded sword belonging to King Charles X of France from a showcase. The thieves climbed up a metal scaffolding and smashed windows on the second floor, breaking into the museum. And in 1990, a painting by Pierre Auguste Renoir, “Portrait of a Seated Woman,” was cut from its frame and stolen from a third-floor gallery.
Surprisingly, Erin Thompson, an associate professor of art crime, said that it was not unusual for museum curators to keep quiet about thefts. “Museum curators thought that if they admitted a theft, they would be exposing a security flaw or inspiring other people to take action,” Dr. Thompson said.
A small percentage of stolen art is luckily found, although studies show that about 40 percent of art stolen from showcases in museums is returned, as those works tend to be more recognizable and their theft is usually noticed right away. However, the missing tragedy of the artworks surely causes a great loss to the museum or a gallery, whether on reputation or actual economic value.
In another case when art is stolen from storage, it can even take museum officials years to notice items are missing. So, how do people protect these precious artworks in advance or track them back as soon as the theft takes place? The solution is the advanced video surveillance solution powered by Artificial Intelligence.
SkyREC, as a video analytics software innovator powered by AI, launches the latest video management software (VMS) — AiMS (Autonomous Intelligent Management System) which brings all the puzzle pieces for video surveillance together to create an ultra-robust and super intelligent solution that meets the requirements of all industries including the art segments.
For any theft or damage caused by humans that occur in the museum or personal gallery, AiMS empowers the police, security officers, or museum/gallery employees to take the most rapid action on loss prevention, or execute proactive post-event investigations.
Here is how AiMS takes the video surveillance system to new heights in a museum or gallery scenario.
In a typical story that we often hear about the museum heist, an unidentified man is seen being allowed inside the Isabella Stewart Gardner Museum in Boston, against Museum policy, by a security guard in March 1990. The man was also seen getting out of a car matching the general description of one reported to be parked outside the museum minutes before the theft.
Exactly 24 hours later, two thieves dressed in Boston police uniforms entered the museum through the same door by telling the security guard at the watch desk that they were responding to a report of a disturbance. Once again, against museum policy, the guard let the men into the museum. The thieves handcuffed the museum’s two guards on duty, put them in separate areas of the museum’s basement, and then stole 13 works of art worth an estimated $500 million in 81 minutes.
To avoid any similar heist occurs, SkyREC AiMS has evolved from security video management to an advanced role to support greater protection. Object Focus, Object Search, Appearance Focus, and Behavior Focus of AiMS are the key functions of being an AI-powered search engine, enabling the police or security officers to rapidly detect and track target objects or specific incidents, reducing the time on searching for security video footage from hours to just minutes, or seconds short.
Object Focus
Object Focus performs logical reasoning of the system to provide real-time detection, analyzing, and tracking meaningful objects to different scenarios. As AiMS learns, thinks, and optimizes itself day by day, the accuracy of video analytics continues strengthening on the face, head, human, and vehicle recognition, which greatly benefits the live monitoring and on-demand modes.
Security operators or security guards of the museum or gallery just need to put the conditions of their preferred highlight target to AiMS, and it will automatically recognize the object which is required attention from the live streams of hundreds or thousands of cameras. After setting, Object Focus pops out the notifications by highlighting the target objects without having the security officers stare non-stop at the cameras and losing focus from dozens of monitors.
Where there is a discrepancy or a suspicious situation, like a person shows up in the exhibition hall after the open hours, or an intruder breaks into a restricted area, AiMS Object Focus immediately detects the objects and sends notification on the monitor, so the operators can inform the security guards on-site by radio communication, mobile phone or pager to ensure protect actions can be taken right away.
Object Search
To power up the very limited visual intelligence capabilities of surveillance cameras (especially regular IP cameras, which are the most common system investments for security purposes due to budget concerns), either in indoor or outdoor scenes, Object Search quickly identifies specific objects based on a human face, head, and body or vehicle out of a single or crowded scene.
Just one click, searching multiple objects simultaneously in any area of interest coming up with a powerful searching result will be complete within seconds or even milliseconds. Then, the operator can select suspicious images to bookmark for further video applications such as Appearance Focus or Behavior Focus. Object Search shows a new way of video search to restore the truth and navigate investigators to the specific moment of an event in seconds.
The odds of catching a perpetrator in the act of crime, and thus prevent loss of exhibits, improve the less time is used for preliminary alarm checks (response to alarm activation) and the faster the actual intervention (attempts at catching the perpetrator) can be launched.
Should a burglary be detected by AiMS, the police can be notified and use the system to search suspects or getaway cars between a specific area or period immediately, which saves valuable time otherwise required for preliminary alarm checks.
Appearance Focus
Once the initial lockdown of the target object is done with Object Search, another innovative searching function, Appearance Focus provides ultra-robust search results to fulfill its mission to empower the investigation efficiency.
SkyREC Appearance Focus achieves complex tasks on video search by enabling user-friendly, detailed visual instructions and powerful feedback. First, Appearance Focus enables users to filter hours of security video footage within milliseconds to quickly pinpoint the target objects.
Next, users have great flexibility to customize their search conditions by setting critical physical descriptions like clothing type, clothing color, accessories, face mask, gender, age, moving direction, posture, behavior, vehicle type, or vehicle color categorization. In addition, users are also allowed to upload the picture of the target to fasten the investigations.
With an advanced search engine design beyond the current VMS in the market, Appearance Focus empowers apparel recognition and vehicle recognition models which are standard functions of an AI Video Management Software to be more innovative and agile.
Behavior Focus
Whether the police finds out if a museum heist or gallery vandalism is simply made by an individual criminal, or planned by an organized crime, it is crucial to track and analyze the continuous behavior of the suspect(s) to provide the investigators the important traces in order to get back the stolen artworks before being sold on the black market or transferred to particular buyers.
On those post-event investigations requiring details on the crime scene and the surroundings, SkyREC Behavior Focus outperforms other security video systems by bringing superior AI analytics on video recording and playback.
To check wider and deeper into the incidents that occur in the same area on different timelines, Behavior Focus not only synchronizes video playback for all objects by uncovering the beginning and ending time of each behavior on the time bar but also simultaneously zooms in to show the details of each specific target without opening extra display windows. Users can accordingly figure out how the incident occurred and what, when, and where to track next.
In the case of museum theft or gallery vandalism, by using SkyREC AiMS, just with a few steps, stolen masterpieces can be quickly and precisely tracked leveraged by the power of AI Video Analytics to bring back the losses caused by the art criminals.
At first, after the heist, theft, or vandalism occurred and being reported, the investigators of police use Object Search in the crime scene to search potential suspects during a specific period by face, head, or human body. The apparel search conditions of the suspects which are reported by the security guard or witnesses can then be applied on Appearance Focus for a speedy search on specific people.
After filtering scenes of massive recorded videos in and out of the museum rapidly, the initial result shows the related images of a stealing staff that took away a painting from the museum warehouse and one getaway car near the museum. The police then can use clues as to the search conditions on Appearance Focus to speed up finding out other associates by searching apparel and vehicle conditions.
In addition, in order to expedite reviewing important videos, the investigators can use Behavior Focus that assists them to search persons and vehicles at the same time with one click. Thus, the result is shown in a window that offers the respective time within different time bars. Additionally, it benefits the police to collect more evidence and unveil the details of the theft process to prevent future losses.
During this complicated investigative process, bookmarking the key images allows the investigators to star important images as if notes making to instantly review them anytime and thus systematically reveal the whole picture of an incident and even track to the major criminal behind the scene.
In short, SkyREC AiMS is dedicated to saving human efforts by effectively digging up the essential threads of a crime through video footage and quickly reporting the route or last-known location of the target objects; it is perfectly designed to provide the most robust protection whether to public spaces such as museums, or private spaces like personal galleries.
