Exclusive: Human operators the weakest link in security systems, says Optimized Electrotech’s Sandeep Shah

Conventional Surveillance systems are being used ubiquitously at public and private installations. Cameras are considered a fundamental commodity for setting up any surveillance infrastructure, but at the same time, 24×7 monitoring of hundreds or thousands of video feeds by operators doesn’t serve the purpose of providing proactive surveillance and quick response to breaches. The main function of video surveillance is to observe public places or the perimeter of secure facilities in order to protect them from theft, intrusion, fire, and any other possible danger.

“No matter how good the cameras and VMS are, the weakest link in the security system is the human operators. The problem is that people can’t keep an eye on multiple screens all the time without losing concentration, which eventually can lead to missing critical events,” says Sandeep Shah, Co-Founder & MD at Optimized Electrotech. According to him, “On top of that, people are prone to fatigue, which inevitably results in a decline in productivity and response time and increases the possibility of human error. Manual or Post Live Analysis of imagery leads to delayed responses, and can also lead to under reporting on critical intelligence.”

Following are excerpts:

What are different types of Artificial Intelligence?

Cloud computing refers to the on-demand delivery of IT services/resources over the internet. On-demand computing service over the internet is nothing but cloud computing. By using cloud computing users can access the services from anywhere whenever they need.

Edge Computing

Computation takes place at the edge of a device’s network, which is known as edge computing. That means a computer is connected to the network of the device, which processes the data and sends the data to the cloud in real-time. That computer is known as “edge computer” or “edge node”. Edge computing brings processing and storage systems as close as possible to the application, device, or component that generates and collects data. This helps minimize processing time by removing the need for transferring data to a central processing system and back to the endpoint. As a result, data is processed more efficiently, and the need for internet bandwidth is reduced. This keeps operating costs low and enables the use of applications in remote locations that have unreliable connectivity. Security is also enhanced as the need for interaction with public cloud platforms and networks is minimized. Edge computing is useful for environments that require real-time data processing and minimal latency. This includes applications such as autonomous vehicles, the internet of things (IoT), software as a service (SaaS), rich web content delivery, voice assistants, predictive maintenance, and traffic management.

Fog Computing

It is an extension of cloud computing. It is a layer in between the edge and the cloud. When edge computers send huge amounts of data to the cloud, fog nodes receive the data and analyze what’s important. Then the fog nodes transfer the important data to the cloud to be stored and delete the unimportant data or keep them with themselves for further analysis. Fog computing places a decentralized enterprise computing layer between the source of data and a central cloud platform. Like edge computing, fog computing also brings the processing power closer to where the data is extracted from. While fog computing enhances efficiency, it can also be leveraged for cybersecurity and regulatory compliance. The term ‘fog computing’ was coined by Cisco — just like fog is formed close to the ground, fog computing takes place close to the network edge. Wearable smart devices such as fitness trackers are an excellent example of fog computing. Such devices rely on linked smartphones to process the data they collect and instantly show the output to the user. This removes the need for these devices to transmit data to a remote cloud platform that the manufacturer would probably need to create and maintain.

How does AI boost surveillance?

Artificial intelligence for video surveillance utilizes computer software programs that analyze the audio and images from video surveillance cameras in order to recognize humans, vehicles, objects, attributes, and events. Security contractors programme is the software to define restricted areas within the camera’s view (such as a fenced off area, a parking lot but not the sidewalk or public street outside the lot) and program for times of day (such as after the close of business) for the property being protected by the camera surveillance. The artificial intelligence (“AI”) sends an alert if it detects a trespasser breaking the “rule” set that no person is allowed in that area during that time of day.

The AI programme functions by using machine vision. Machine vision is a series of algorithms, or mathematical procedures, which work like a flow-chart or series of questions to compare the object seen with hundreds of thousands of stored reference images of humans in different postures, angles, positions and movements.

In recent years, authorities particularly in the United States and the European Union have moved quickly to integrate “smart border” AI capabilities into their operations, heralding a potential game-changing moment for the ability of governments to patrol their borders.

What are the challenges faced by Border Management at Night?

Indian borders are amongst the longest borders in the world, we have land borders of over 15000+ Kms, which are managed by Indian Army, Border Security Forces, Indo-Tibetan Border Police, Sashastra Seema Bal, and Assam Rifles.

We also have almost 8000 Kms of Coastal borders protected by Coast Guard of India and Indian Navy. Where coastal borders pose the challenges of being part of turbulent seas, the land borders are riddled with geographical, topographical, and climatic conditions which make them hard to manage. Night means the problems are exponentially increased, as the borders are not only tough to navigate, look at or man properly, at night they are even impossible to look at. The advent of Night Vision has started to curb this problem, where the forces have been able to make “Night into Day”, however, there are still a number of issues that are critical to national security. A few of the highlighted issues are:

Detection of movement at night: Most Conventional surveillance systems are not able to understand the change in imagery or detect the movements of enemies or smugglers

Illegal Smuggling: Drugs, animals, or human trafficking is one of the major issues border services are dealing with on a daily basis

IFF: Identification of Friend or Foe, conventional night vision devices makes it very difficult to clearly identify friendly or enemy units from a distance. Active Long Range IFF is required, which is possible with image fusion and Artificial Intelligence

Manoeuvrability: Night driving, Night Flying or Night Navigating is possible but with great limitations with the current night vision devices ecosystem. Lack of Depth Perception being the biggest problem. Modern Imaging techniques can solve these

Perimeter Intrusion Detection: The current systems utilize multiple sensors with floodlights and CCTVs/NVDs to detect if the perimeter has been breached; however, there are number of instances which can trigger the system resulting in far greater false alarms than necessary. AI can help reduce these with a better object classification and threat analysis

Aatmanirbhar Bharat initiative: What is the company doing for the Indian armed forces?

We have indigenously designed, developed, and manufactured Intelligent Surveillance Platforms which have far ranging applications in Land, Air, and Naval Defence Surveillance. We have products that cover the entire Electro-Magnetic spectrum providing mission critical intelligence in all weather or light conditions. Our Vision series of products have Long Range Surveillance capacities with proven ranges for Detection at 30 Kms and future products planned for 50Kms as well. Our EYE series of products are strategic in nature and can be deployed for restricted access control and clandestine perimeter security. The Eye series products are smaller in scale and have a low power factor. All of our products are AI enabled and as such can be used as unmanned systems; this reduces human error, false alarms, and increased situational awareness. Our AI onboarded systems also mean that our brave soldiers have enough time to respond in case of an emergency.

Any solutions for paramilitary as well as defence forces?

We are also developing Electro Optical weapon sights which have long ranges for detection, these weapon sights are also AI-enabled and help in better target acquisition. Our Sights offer the war fighters a tactical edge on the field while maintaining strategic control on their equipment. We also offer our perimeter security options to paramilitary forces, which include Optical Sensors, 360 degree Surveillance systems and Wide Area Persistent Surveillance systems.