Oded Sagee, Senior Director of Embedded and Integrated Solutions at Western Digital Corporation, discusses how surveillance has moved forward in the world, and how this has happened
With increased demands being placed on safety and security globally, and supported by advancements in IP cameras and 360-degree camera technology, the video surveillance industry is growing steadily.
Surveillance cameras are now common in and around government buildings, military posts, businesses, banks, transportation centers, casinos, shopping malls, sports venues, historic landmarks, schools, and many more.
Surveillance isn’t just about security any longer. In many cases, it’s about extracting value and intelligence from the video captured.
This could include gaining a better understanding of retail shopper behaviors, or for managing traffic congestion, or to manufacture products or operations more efficiently. Seeing a drone flying over a construction site or farmland capturing video nowadays is no longer unusual.
Today’s surveillance systems collect huge amounts of data, but only a small amount is actually utilized. The data collected is analogous to an insurance policy. Unless a security incident occurs, you typically do not need the data, or insurance.
However, the data collected can be extremely valuable for other types of business or operational insights that are not about protection and security, but about commerce, efficiency, solving problems, as well as support for other location or context-based applications.
With all of this activity and intelligence to be gained, the video surveillance market is burgeoning in growth. Valued at over $30 billion in 2018, the market is expected to reach $68 billion in revenue by 2023, at a CAGR of 13.1 percent (from 2018 to 2023).
What has changed in surveillance is not how data is captured, but how it can be used to drive actions, not only to support ‘fast data’ applications that analyze data as it is collected (in real-time), but also to support big data applications that analyse data in the future when required.
It’s no longer about just storing data, but what we can do with it once captured that is fueling a new generation of ‘smart’ video applications.
What is Smart Video?
Smart video is about the shift from imagery to insights, from simply collecting data for forensic and backwards-viewing, to analysing and understanding the context of the data captured.
It uses artificial intelligence (AI) and algorithms derived from big data applications to provide immediate insights and forward-looking predictions.
To fully understand video surveillance, it is important to know the difference between content and context relating to data.
The endless hours of unfiltered video captured by surveillance cameras is content. As this raw content is processed in real-time, the value, intelligence or actionable insights extracted from the data is referred to as context. Examples of context in video surveillance include:
- Parking space management where analytics can be used to determine peak hours of operation, handicap parking use, areas of congestion, average parking durations, and unmoved vehicles.
- Customer retail buying preferences where analytics can be used to determine how many people entered the store, their gender and ages, in-store time spent, and traffic generated by the new kiosk.
- Agricultural drone surveillance where analytics can be used to survey a farm and surrounding land, diagnose vegetation and crop health, determine possible yields, track livestock and food consumption, as well as insect and pest populations.
- Smart city scenarios where analytics can be used to provide safety and evacuation information, and can coordinate with weather and traffic data to create the fastest evacuation routes out of a city.
Facial Recognition
There are many use case examples that can validate the value of analysing captured surveillance video, but facial recognition is certainly a frontrunner.
As an example, authorities may be looking for a missing person with mental incapacities who may need help. They believe the individual entered a store and left.
In a big data application, someone would have to review tons of captured video, looking backwards to find evidence of this lost soul in the store, and possibly perform some additional analysis on the data to determine his actions, identify the time the person entered or left the store, and take some action. In this example, big data analysis is performed after the event has occurred.
Utilising AI and algorithms derived from big data applications, fast data applications respond to events as they occur.
Once the citizen entered the store, a fast data app could then perform real-time facial recognition from the video feed, comparing the citizen’s face to a database library of facial signatures.
If the facial signature is detected, the application can trigger a security alert to help the citizen in distress and get him safely back home.
The Data Storage Strategy
With commoditisation of compute power, coupled with advancements in flash technology, surveillance cameras can do more than just capture streams of video to feed to a networked video recorder (NVR), or in the case of an enterprise, transfer all of the footage to a cloud data centre.
As more compute power is being driven to the edge, we’re also seeing the evolution of more data analytics happening there as well.
A typical 1080p or 4K camera can capture large data streams. Moving the data to a centralized location for analysis can be expensive, but also a potential point of failure or security breach. More importantly, the quality of service can be damaged by the lack of connectivity.
Can you imagine if an event was triggered and the surveillance camera couldn’t capture it, let alone send out an alert because of glitches in connectivity or a sudden drop in network availability?
Therefore, it is mission critical for the surveillance system to be able to collect video whether the cameras are connected to an NVR, to edge storage units, or on the individual surveillance camera itself.
Collecting the data is the basis of a surveillance system and the most critical point of failure in many implementations.
Relying on the always-on connectivity between the camera and a recording device is a risky strategy. What happens if the network is not available due to a technical issue, weather conditions, or a deliberate attack?
As big data gets bigger and faster, and fast data gets faster and bigger, the storage strategy is to not funnel all of the video content to the main server, which is expensive and dependent on network availability, but instead, use a combination that stores data locally at the camera-level, as well as an edge gateway that enables video and data to be aggregated at various distances from the edge, and back to the cloud where the content typically resides for future use.
A video surveillance system that uses edge cameras and a comparable storage strategy will reap high system and service reliability, low TCO, and the ability to scale without adding expensive recorders or servers.
Evolving Camera Technologies
The need to provide intelligent capabilities within video surveillance, coupled with the development of cloud-based surveillance systems, has led to the evolution of a smart breed of cameras at the network’s edge.
These edge-based cameras have a powerful computing element and capable storage device implemented within that enables local capture and analysis (where the data is generated and lives), providing insights in real-time, without the effects of network availability or latency.
These cameras are technologically evolving as well, extracting the details and quality required to drive insights andare typically low profile, quiet, power efficient, and operable in wide temperature ranges.
Optical zoom and motion range capabilities are now expanding as well as improvements in signal-to-noise (S2N) ratios, light sensitivities (and the minimum illumination needed to produce usable images), wide dynamic ranges (WDR) for varying foreground and background illumination requirements, and of course, higher quality resolutions.
Network Failsafe
Surveillance cameras are typically connected to an NVR that acts as a gateway or local server, collecting data from the cameras and running video management software (VMS), as well as analytics. Capturing this data is dependent on the communications path between individual cameras and the NVR.
If this connection is lost, whether intentional, unintentional, or a simple malfunction, surveillance video will no longer be captured and the system will cease operations.
A number of failsafe mechanisms can be deployed from using multiple cameras to cover overlapping areas, to RAID solutions on main storage, or memory cards deployed within individual cameras and distributed storage systems.
Storing data inside a surveillance camera has become the failsafe mechanism used most often in the event that connectivity to the NVR or cloud is lost.
In this scenario, the camera can still record and capture raw footage locally until the network is restored.
Final Thoughts
Fast data applications for smart video are endless and have only scratched the surface of real-world use. We amass and generate large amounts of information from the increasing number of data points captured by such edge devices as surveillance cameras.
Applying analytics to real time captured data is driving new smart video applications whose video streams extract value and intelligence that drive actionable insights.
The ability to add local storage to and have enough built in compute power to enable real-time data analytics in the camera itself, will make every edge unit in the surveillance system a smart and independent subsystem.
About the author
Oded Sagee is Western Digital’s Senior Director of Embedded & Integrated Solutions. He is responsible for developing and driving product go-to-market strategies for both the evolving mobile and compute markets, as well as the fast growing automotive, connected home, smart city, industrial, IoT and surveillance segments.
Sagee brings a diverse background with more than 20 years of high-tech experience in a variety of executive-level positions in marketing and business development capacities. He is a thought leader on embedded solutions for vertical markets and has been published in notable trade publications.
Sagee has earned a Bachelor’s of Law degree in Commercial Law, as well as a Master’s of Business Administration degree, both from the London Business School (LBS).
About Western Digital
Western Digital is a company with strong values and a passion to innovate and lead the charge in the transformation of data.
Creating the right environment where our employees can thrive is key to how we do business. Quality products, exceptional customer service and industry-leading solutions all come from a culture that’s inclusive, forward-thinking and bold enough to imagine the possibilities of data.
We thrive on the power and potential of diversity. As a global company, we believe that the most effective way to embrace the diversity of our customers and communities is to mirror it from within.
We believe that the fusion of various perspectives results in the best outcomes for our employees, our company, our customers, and the world around us.
We are committed to an inclusive environment where every individual can thrive through a sense of belonging, respect and contribution.
The post Delivering smart and actionable insights in video surveillance appeared first on Security Buyer.