Skip to main content

Your next security camera could record videos only machines can understand

(Image credit: Mi)

Video is the biggest consumer of cloud storage, compute and bandwidth in the world. So anything that can reduce its gargantuan appetite for resources could save a significant amount of both time and money.

Enter Fujitsu with a new compression algorithm that, it says, can reduce the size of a video by 90%. The not-so-insignificant caveat is that the resulting video can only be interpreted by artificial intelligence (AI) because of the level of degradation.

The key aspect of the new technology - developed by scientists at the Japanese firm - is that it automatically analyzes areas within an image that AI prioritizes and compresses data to the minimum size that AI can recognize.

Great for the cloud

This, Fujitsu added, “will allow users to analyze more advanced video data by combining multiple video data stored in the cloud, sensor data, and performance data such as sales data”, all without any increased data transmission demands.

In practice, compression will be conducted at the edge (on the device itself) using a specialist chip, and recognition performed in the cloud - the two are joined up in a continuous feedback loop.

The rise of ultra high resolution cameras on smartphones (the Samsung S20 Ultra has a 108 megapixel camera) and 4K security CCTV cameras has made such technologies a necessity.

Fujitsu will make the technology available to third parties by the end of fiscal 2020, and introduce it into a variety of applications for different industries.