Artificial Intelligence, Video Analytics & Innovative Solutions
Artificial Intelligence (AI) is transforming how we operate and rely on technology, enabling us to work more efficiently and effectively than ever before, making our jobs simpler, our efforts more calculated and our outputs more accurate. Similarly, AI is impacting our security and surveillance systems, where AI meets traditional surveillance practices: intelligent video analytics. Plus new innovative products have transformed the way of surveillance now a day…
When we hear the term “Artificial Intelligence,” images of aliens, spaceships landing on Earth come to mind. While not exactly the extraterrestrial scene we may envision, Artificial Intelligence, or AI, is bringing human intelligence to everyday technologies. We are now able to form a relationship with our technology, use it to make our security measures intelligent. Surveillance systems that include video analytics analyze video footage in real-time and detect abnormal activities that could pose a threat to an organization’s security. Essentially, video analytics technology helps security software “learn” what is normal so it can identify unusual, and potentially harmful, behavior that a human alone may miss. It does this in two ways; first by observing objects in a monitored environment and detecting when humans and vehicles are present, and second by taking operator feedback about the accuracy of various events and incorporating this intelligence into the system itself, thus improving its functionality. This interaction between operator and technology results in a “teachable” system: Artificial Intelligence at its best in the realm of security where ultimately, human oversight takes a backseat to the fine-tuned capabilities of intelligent video analytics. Eliminating human error is a key driver behind bringing Artificial Intelligence to security through intelligent video analytics. Studies have shown that humans engaged in mundane tasks have a directed attention capacity for up to 20 minutes, after which the human attention span begins to decrease. In addition, when humans are faced with multiple items at one time, attention spans will decrease even more rapidly. Therefore, video analytics are beginning to take the place of initial human judgment in an effort to increase operational efficiency. While a security officer might miss a person sneaking into a poorly lit facility, a camera backed with intelligent video analytics is designed to catch a flash on the screen and recognize it as a potential threat. Or it will spot a person loitering at the perimeter of a schoolyard and alert on-the-ground security officials to investigate and take action if necessary, all without missing a beat and keeping close watch on the many cameras and locations. Rather than depend on solely human monitoring, AI-powered systems instead notify security teams of potential threats as they happen, helping businesses prevent break-ins or illegal activity, as well as increasing human accuracy. Artificial Intelligence helps people do their jobs better, thereby making our lives easier and our locations safer. Whether securing our businesses, cities or homes, or providing more curate online shopping and entertainment experiences, Artificial Intelligence is making technology more personal and purposeful than ever before.
While some traditional security measures in place today do have a significant impact in terms of decreasing crime or preventing theft, today video analytics gives security officers a technological edge that no surveillance camera alone can provide.
Video Analytics for Real-Time Detections & Alerts
Through the implementation of various image processing algorithms, Video Analytics can detect a variety of events, in real-time, such as, Penetration of unauthorized people / vehicles into restricted areas, Tailgating of people / vehicles through secure checkpoints, Traffic obstacles, Unattended objects, Vehicles stopped in no-parking zones, highways or roads, Removal of assets, Crowding or grouping, Loitering and more. By defining the set of events that the surveillance system operator wants to be alerted to, the Video Analytics software continuously analyzes the video in real-time and provides an immediate alert upon detection of a relevant event.
Video Analytics algorithms may be implemented to analyze recorded video, a task that is challenging and time consuming for a human operator, especially in cases whereby a large amount of video must be reviewed. Through rapid analysis of recorded video, Video Analytics can pinpoint an event in recorded video, and retrieve the relevant video segment from the stored video. Through the use of search queries, the surveillance system operator defines the event desired in a specific segment of recorded video. The Video Analytics system analyzes the video and provides the search results through an automated search, without requiring any additional intervention from the operator. Video Analytics algorithms can also analyze recorded video to extract statistical and operational data. Rather than having an operator manually review the video and tally all the people or cars moving in a certain area, or checking which traffic routes are most commonly taken, Video Analytics can perform these tasks automatically. The surveillance system operator defines the data required as well as the time period to be analyzed, and the Video Analytics system provides results following an automatic review of the recorded video. No manual review is required by the operator.
The use of video surveillance within public transport is no longer only a matter of incident evidence, even if the vast majority of respondents (86%) find this forensic element the most valuable concrete use. Real-time detection of incidents also scored highly in terms of potential value (72%), indicating this is a trend to come. Already today, 42% of respondents can share live video with other parties such as police or other authorities, and 50+% plans on using real-time video surveillance in “rolling stock” (moving vehicles vs. just in static locations). This underlines the value of real-time video surveillance monitoring across all areas of a public transport system. The majority of respondents were aware of video detection analytics for intrusion, perimeter breach, fire & smoke and rail track access, with actual usage already between 10-20%. Future interest is high with approximately half of the respondents having indicated that they are interested in using these video analytics applications moving forward. Graffiti behavior detection was a further application which sparked the interest of over half the respondents.
The market share for video analytics is predicted to grow from $1,537.9m in 2015 to $3971.2m by 2020, according to the latest report released by Marketsandmarkets. At this rate the market’s Compound Annual Growth Rate (CAGR) would stand at a handsome 21% annually for the period 2015-2020.
Some latest innovations in the market
Spherical, throw able Explorer camera for police departments
Sized similarly to a softball, the Explorer is designed to be thrown into dangerous environments and instantly send panoramic images to an Android or iOS mobile device, thereby giving them more information about any potential dangers that may lie ahead. The Explorer contains one camera with six separate lenses, a setup chosen because of its lower cost and reduced complexity compared to fitting the ball with six separate cameras. The outer layer consists of a thick rubber shell which Bounce Imaging tests to military standard MIL-STD 810, dropping the device onto concrete 26 times from a height of 4 ft (1.2 m) and 26 times from a height of 7 ft (2.1 m) to ensure it can withstand being tossed into buildings and landing on hard surfaces. Once activated, the device’s cameras take a few monochrome WVGA (800 x 480) images every second. These are run through a single processor, with image-stitching software developed by engineers at the Costa Rican Institute of Technology producing a single 360-degree panoramic image of the ball’s surrounds. It is this image-stitching technology that Bounce Imaging CEO and Explorer inventor Francisco Aguilar highlights as the key innovation that makes the device possible. Unlike other methods that can take around a minute to combine multiple images into a single panorama, the software’s algorithms can achieve this in a fraction of a second.
Video surveillance in a lightbulb
Sengled, the smart lighting company, has unveiled a lightbulb that combines Wi-Fi connectivity with LED light and a 1080p security camera into one innovative product. Usable both indoors and outdoors the Sengled Snap is a 2015 CES Best of Innovation Award winner. The Snap will cost $199 when it becomes available later this spring.
Sony SmartEye turning any glasses into CCTV camera
Sony’s SmartEye, their answer to Google Glass, has been described as like wearing a CCTV camera on your head and like Google Glass it comes with a head-up display to show information in front of your eyes.
More interesting is their CES 2015 unveiling of the Smart-Eyeglass Attach, a small module which can make regular glasses smart. While currently only a prototype, it’s easy to imagine how technologies like the Attach could be used by security guards, police and lone workers to improve video surveillance.
3D printed Surveillance Masks
Chicago-based artist Leo Selvaggio has started URME Surveillance, who aims to produce a prosthetic mask that could potentially render CCTV tracking and tracing obsolete. Different levels of product will be available, from inexpensive paper versions, to state-of-the-art 3D-printed models. One of the most widely deployed police and NSA surveillance systems is called Virtual Shield, and can not only track you, but can also pull up all of our corresponding information as well. The URME mask would make this impossible. In addition to facial recognition, new systems are also using other biometric and physical identification and diagnostic methods – coding and track individual walking signatures, as well as voice print signatures.
Conclusion
Today’s surveillance systems are no longer just monitoring equipments but much more doing with video analytics, Artificial Intelligence and humanizing technologies. Also the innovative technology is geared up with next-generation equipments.
