The Russian developer of computer solutions Smart Engines has patented in the US an artificial intelligence solution that allows the parameters of three-dimensional space to be restored from a two-dimensional image. The technology developed by the company can be useful in the field of unmanned vehicles, in the field of document recognition and other areas. This is the company’s sixth patent in the US in 2023, Smart Engines told RB.RU.
Thanks to technology, artificial intelligence can now detect partially obscured objects and complete their shape.
As the company explained, the neural network architecture combines the blocks used in neural networks with traditional real-world image analysis tools: the Hough transform.
These two mechanisms work simultaneously and complement each other. Smart Engines highlights the advantages of the resulting neural network architectures in terms of protecting against attacks against AI.
“Thus, even replacing part of the image will not be an obstacle to detecting an object. For example, if in an image of a road the vanishing point is accidentally or intentionally obscured by some object, the Hough neural network will still find it,” the company explained.
In early November, Smart Engines received a US patent for its AI “stopping” technology. The method is mainly relevant for solving text recognition problems in a video stream: the decision to “stop” the AI is made based on a forecast of the future.
And in October, the company introduced technology for banking applications that allows payments using QR, phone number and card number in a single flow.
Author:
Natalia Gormaleva
Source: RB
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
