Advertisement
Published in:
01-11-2022 | The Hansen Report
Products
Published in: ATZelectronics worldwide | Issue 11/2022
Log inActivate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by (Link opens in a new window)
Excerpt
Teraki, an AI-software company based in Berlin (Germany), has launched new radar recognition software that can identify stationary and moving objects with high precision and low computing power. The Real-Traffic solution runs on Infineon's ASIL-D compliant AURIX-TC4x microcontrollers. The machine learning approach used is reported to be able to overcome interference and fulfill the very high accuracy requirements by processing raw data and reducing noise. This results in more points per object and hence fewer false alarms and hence more safety. The algorithm reduces the radar signals according to the first Fast Fourier Transformation (FFT) and thus achieves a factor of 25 lower error rate for missing objects for the same RAM/fps. Compared to CFAR, the accuracy of the classification is up to 20 % higher and the number of valid recognitions increases by 15 %.
© Infineon
× ![]()
…
