Specialist Complete Security Systems

When will AI trasnform surveillance?

Posted by: Alastair Dodwell In: AI, Blog 27 Jan 2018 0 comments

AI or Artificial Intelligence is changing the security industry with the power and scope of always on networked computers.

We usually think of surveillance cameras as digital eyes, watching over us or watching out for us, depending on your view. But really, they’re more like portholes: useful only when someone is looking through them. Sometimes that means a human watching live footage, usually from multiple video feeds. Most surveillance cameras are passive, however. They’re there as a deterrence, or to provide evidence if something goes wrong. Your car got stolen? Check the CCTV.

But this is changing — and fast. Artificial intelligence is giving surveillance cameras digital brains to match their eyes, letting them analyze live video with no humans necessary. This could be good news for public safety, helping police and first responders more easily spot crimes and accidents and have a range of scientific and industrial applications. But it also raises serious questions about the future of privacy and poses novel risks to social justice.

A recent article by James Vincent published the Verge makes interesting reading and asks probing questions about trust in Governments. – What happens when governments can track huge numbers of people using CCTV? When police can digitally tail you around a city just by uploading your mugshot into a database? Or when a biased algorithm is running on the cameras in your local mall, pinging the cops because it doesn’t like the look of a particular group of teens?

These scenarios are still a way off, but we’re already seeing the first fruits of combining artificial intelligence with surveillance. IC Realtime is one example. Its flagship product, unveiled last December, was billed as Google for CCTV. It’s an app and web platform named Ella that uses AI to analyze what’s happening in video feeds and make it instantly searchable. Ella can recognize hundreds of thousands of natural language queries, letting users search footage to find clips showing specific animals, people wearing clothes of a certain color, or even individual car makes and models.

AI SURVEILLANCE STARTS WITH SEARCHABLE VIDEO

In a web demo, IC Realtime CEO Matt Sailor showed The Verge a version of Ella hooked up to around 40 cameras surveilling an industrial park. He typed in various searches — “a man wearing red,” “UPS vans,” “police cars” — all of which brought up relevant footage in a few seconds. He then narrowed the results by time period and location and pointed out how users can give thumbs-up or thumbs-down to clips to improve the results — just like Netflix.

Let’s say there’s a robbery and you don’t really know what happened,” says Sailor. “But there was a Jeep Wrangler speeding east afterward. So we go in, we search for ‘Jeep Wrangler,’ and there it is.” On-screen, clips begin to populate the feed, showing different Jeep Wranglers gliding past. This will be the first big advantage of combining AI and CCTV, explains Sailor: making it easy to find what you’re looking for. “Without this technology, you’d know nothing more than your camera, and you’d have to sift through hours and hours and hours of video,” he says.

Ella runs on Google Cloud and can search footage from pretty much any CCTV system. “[It] works well on a one-camera system — just [like] a nanny cam or dog cam — all the way up to enterprise, with a matrix of thousands of cameras,” says Sailor. Users will pay a monthly fee for access, starting at around $7, and scaling up with the number of cameras.

IC Realtime wants to target businesses of all sizes but thinks its tech will also appeal to individual consumers. These customers are already well-served by a booming market for “smart” home security cams made by companies like Amazon, Logitech, Netgear, and the Google-owned Nest. But Sailor says this tech is much more rudimentary than IC Realtime’s. These cameras connect to home Wi-Fi and offer live streams via an app, and they automatically record footage when they see something move. But, says Sailor, they can’t tell the difference between a break-in and a bird, leading to a lot of false positives. “They’re very basic technology that’s been around for years,” he says. “No AI, no deep learning.”

That won’t be the case for long. While IC Realtime offers cloud-based analytics that can upgrade existing, dumb cameras, other companies are building artificial intelligence directly into their hardware. Boulder AI is one such startup, selling “vision as a service” using its own standalone AI cameras. The big advantage of integrating AI into the device is that they don’t require an internet connection to work. Boulder sells to a wide range of industries, tailoring the machine vision systems it builds to individual clients.

“The applications are really all over the board,” founder Darren Odom tells The Verge. “Our platform’s sold to companies in banking, energy. We’ve even got an application where we’re looking at pizzas, determining if they’re the right size and shape.”

Odom gives the example of a customer in Idaho who had built a dam. In order to meet environmental regulations, they were monitoring the numbers of fish moving making it over the top of the structure. “They used to have a person sitting with a window into this fish ladder, ticking off how many trout went by,” says Odom. (A fish ladder is exactly what it sounds like: a stepped waterway that fish use to travel uphill.) “Then they moved to video and someone [remotely] watching it.” Finally, they contacted Boulder, which built them a custom AI CCTV system to identify types of fish going up the fish ladder. “We really nailed fish species identification using computer vision,” Odom says proudly. “We are now 100 percent at identifying trout in Idaho.”

If IC Realtime represents the generic end of the market, Boulder shows what a boutique contractor can do. In both cases, though, what these firms are currently offering is just the tip of the iceberg. In the same way that machine learning has made swift gains in its ability to identify objects, the skill of analyzing scenes, activities, and movements is expected to rapidly improve. Everything’s in place, including the basic research, the computing power, and the training datasets — a key component in creating competent AI. Two of the biggest datasets for video analysis are made by YouTube and Facebook, companies that have said they want AI to help moderate content on their platforms (though both admit it’s not ready yet). YouTube’s dataset, for example, contains more than 450,000 hours of labeled video that it hopes will spur “innovation and advancement in video understanding.” The breadth of organizations involved in building such datasets gives some idea of the field’s importance. Google, MIT, IBM, and DeepMind are all involved in their own similar projects.

IC Realtime is already working on advanced tools like facial recognition. After that, it wants to be able to analyze what’s happening on-screen. Sailor says he’s already spoken to potential clients in education who want surveillance that can recognize when students are getting into trouble in schools. “They’re interested in preemptive notifications for a fight, for example,” he says. All the system would need to do would be to look out for pupils clumping together and then alert a human, who could check the video feed to see what’s happening or head over in person to investigate.

This is fascanating stuff and an area we will be wathcing closely.

Preventing crime at your business

Posted by: Alastair Dodwell In: Blog 14 Nov 2017 0 comments

A great deal of Crime is preventable, and safeguarding your businesses through the use of technology is a critical component in risk reduction. Once key component recommended by CSC is the use of CCTV.

Effective deployment of CCTV

A shocking statistic that you might be unaware of is that for every 100 crimes, an average of 16 are prevented through the use of CCTV. If a business hasn’t already installed a CCTV system, it is already at risk and criminals who want to commit horrendous crimes against that business can instantly spot vulnerabilities. It is also known for crime rates (burglaries and vehicle crimes) to reduce in areas that have active CCTV systems.

The benefit of CCTV is that any footage recorded can be used by a police force. For example, if there was no CCTV in place, it could take longer to catch the criminal as detectives would have to search for CCTV in the local area, obtain that footage and then look through it. If a business has been victim to a crime, but has CCTV, it can be a much quicker process; although active CCTV can deter criminals completely from attacking a business.

It is vital to think on your feet when it comes to placing CCTV around your perimeter. It is important to be able to identify people who come and go from the business on a daily basis. From this, you can use the high-quality footage to identify an individual and this will allow police to pick up on certain characteristics that may lead them to the culprits. It may also be necessary to capture vulnerable points to make sure all areas of a business are covered.

See our CCTV overview below.

CCTV Basics

CCTV cameras come in both wired and wireless models. Some of the wired models get their power from the network cable, while others need a mains connection. If you need to place cameras outdoors, or minimise visible wiring, wireless cameras are usually a better choice.

Various types of cameras exist to cover different areas. That might include domed cameras for outdoors, small ‘bullet’ type cameras for doorways, and a more traditional camera on a stand indoors.

Features of CCTV

We recommend that you purchase HD cameras if at all possible. Older cameras with 640×800 resolution are fine for the basics, but they may not present a clear picture, which might be important if you needed to see someone’s face or read a number plate.

Infra-red LED lights will illuminate the area at night and give you a better picture in the dark. Remember that infra-red light, while invisible to our eyes, will reflect off glass. In other words, you can’t point an indoor camera out of the window at night.

For full control and remote access, ask us to supply cameras with pan and tilt technology, so you can move the lens using a smartphone or browser and see a wider viewing angle. You might also choose to have two-way audio, so you can hear what’s going on and speak through the camera. Speaking through the camera may require an external speaker.

Costs and Convenience of a CCTV System

IP based cameras are inexpensive and don’t require masses of wires. You’ll need to decide whether you want footage recorded on-site (on a DVD or SD card), or whether you want footage to be sent to you electronically when motion is detected.

While you can watch your cameras from remote locations, it’s best to have some kind of automation so that you catch intruder activity whenever it occurs.

How to find the weakest link of your access control system

Posted by: Alastair Dodwell In: Blog 01 Oct 2017 0 comments

In end-to-end security, it’s important to consider that the security chain is only as strong as its weakest link. That is why it is essential that an access control system is always evaluated in its entirety, to discover where the weakest link can be found.

It is not uncommon for access control systems to be installed and then used for the longest time possible without any attention to updating the system’s intrinsic security features. There are many systems in the field that are over 10-years old, based on technologies much older than this and with no or very low cyber security protection.

Some ‘weak-links’ might be strengthened by new encryption methods, others by good process and some only by partial or entire replacement. What is essential is that for those considering investing in new technology, not to introduce weak-links.

Cards / biometrics

Cards are an important part of access control systems and for many years have been the most popular form factor for identifying a person at an entrance. Many different types of cards are available from a wide variety of suppliers but to simplify we can focus on Proximity cards (circa 125kHz) and Smart cards (13.56MHz).

Proximity cards are an older technology that for the most part have low security features. Organisations that have retained this technology (especially combined with weigand reader communications – see later) may be well advised to look at newer and more secure alternatives. A few basic internet searches about how to hack the most common proximity technology shows a device for around £30 that can clone a card. This alone would introduce a vulnerability to the access control system that could lead to further security exploitations.

Smart cards can offer enhanced security but there must be diligence about their design. To use a card serial number combined with a weigand output reader is not offering much more protection than using older proximity technology. Amongst the wider feature-set of smart cards, the capability to create secure solutions should be adopted. Future-proofing (ability to adapt) and encryption key ownership are important design factors too. The type of data encryption employed can differ greatly between the various smart card types.

Card to Reader transmission

The transmission of information between the card and the reader provides an opportunity for hacking. This could take the form of eavesdropping or skimming, or could involve pretending to be someone else (spoofing). Encryption is an effective security technique that can be used to counter this.

The most secure method is to have this encryption decoded by the controllers rather than at the reader, because they are usually located on the secure side of the building, however many readers and even systems do not support this.

Readers / antennas

The reader reads the card details and converts it into a wired signal. The reader therefore does not really have to do anything with the information that is on the card. This means that there is no need for decoding to take place in the reader. After all, allowing decoding to take place in the reader would only create a security risk, because the keys for decoding are also held on the reader. This is a risk that must not be underestimated, although many of the solutions in use provide only limited options.

Reader-Controller transmission

The same risks of hacking by eavesdropping, skimming or spoofing that apply in relation to card-reader transmission also apply here. It is therefore important to take care that you are not using a generic protocol such as the popular Wiegand protocol as this is very susceptible to hacking. The ideal solution is to consider the security of the card and the reader and their communications and ensure these are encrypted and future-proof meaning the security can be enhanced if there is a future vulnerability.