IC Realtime, a leader in digital surveillance and security technology has introduced “Ella,” a cloud-based deep-learning search engine that augments surveillance systems with natural language search capabilities across recorded video footage.
“We queried dealers and asked them a series of questions about their biggest challenges; the majority of the answers centered around the inability to find video when archived data is needed,” said Matt Sailor, CEO, IC Realtime. “No matter how good the machine is, or how many megapixels, the real problem is the inability to find things quickly.”
Ella — so named because elephants are known for having long memories — uses both algorithmic and deep learning tools to give any surveillance or security camera the ability to recognize objects, colors, people, vehicles, animals and more. Ella was designed with the technology backbone of Camio, a startup founded by ex-Googlers who realized there could be a way to apply search to streaming video feeds. Ella makes every nanosecond of video searchable instantly, letting users type in queries like “white truck” to find every relevant clip instead of searching through hours of footage. Ella quite simply creates a Google for video.
“The idea was born from a simple question: if we can search the entire Internet in under a second, why can’t we do the same with video feeds,” said Carter Maslan, CEO of Camio. “The original concept wasn’t to retrieve video surveillance but to put together all sorts of photos,” Sailor added. “It was for social media.”
The average surveillance camera sees less than two minutes of interesting video each day despite streaming and recording 24/7. On top of that, traditional systems only allow the user to search for events by date, time, and camera type and to return very broad results that still require sifting, often taking hours of time.
Ella instead does the work for users to highlight the interesting events and to enable fast searches of their surveillance and security footage for the events they want to see and share. From the moment Ella comes online and is connected, it begins learning and tagging objects the cameras sees. The deep learning engine lives in the cloud and comes preloaded with recognition of thousands of objects like makes and models of cars; within the first minute of being online, users can start to search their footage.
“Say you recognize a crime took place and you get a small bit of information,” Sailor explained. “Maybe someone saw a Jeep Wrangler driving away. You can find all instances of a Jeep Wrangler, and share that across any platform. The engine is smart enough to almost anything you wish to find.”
Hardware agnostic, Ella also solves the issue of limited bandwidth for any HD streaming camera or NVR. Based on machine learning algorithms that recognize patterns of motion in each camera scene to recognize what is interesting within each scene, Ella will only record in HD when it recognizes something important. By learning from what the system sees, Ella can reduce false positives by understanding that a tree swaying in the wind is not notable while the arrival a delivery truck might be.
Ella also brings RMR and other revenue opportunities for dealers, Sailor explained. “A lot of customers have cameras installed. They may be a few years old, but they still work well. A lot of new technology is based on hardware, but a city might have 8,000 cameras. Dealers can approach those same customers and sell an amazing solution that is quickly deployable and bring them up to speed without having to sell them a new system.”
Ella subscription pricing starts at $6.99 per month and increases with storage and analysis features needed for the particular scope of each project. To learn more about Ella, visit www.smartella.com.