Machine Learning-Based Advanced Sound Sensing Solution for Detecting Fast-Moving Emergency Vehicles

20 May 2021 - 0 Comments

Infineon Technologies along with Reality AI has created an advanced sound sensing solution that provides the vehicle a sense of hearing for sensing fast-moving emergency vehicles. The new sensing solution combines the XENSIV MEMS microphones with AURIX microcontroller (MCU) and Reality AI’s Automotive See-With-Sound (SWS) system. The new solution has been developed based on a machine learning algorithm, hence they can easily detect emergency vehicles, cars, and other road participants even when they are in the driver’s blind spots.

IM67D130A, the automotive-qualified XENSIV MEMS microphone is suitable for harsh automotive environments as they have an increased operating temperature range from -40 °C to +105 °C. With low distortions (THD) and the high acoustic overload point (AOP) of 130 dB SPL, the microphone can capture distortion-free audio signals in loud environments. This permits a reliable classification, even if the siren sound is hidden in the high background or wind noise.

The audio signal detected is processed by the Reality AI software with the help of Infineon’s AURIX TC3x family of MCUs. The scalable MCU family comes with one to six cores and up to 16 MB of Flash with functional safety up to ASIL-D according to the ISO26262 2018 standard and EVITA full cybersecurity.

Feature of IM67D130A XENSIV MEMS Microphone

The high dynamic range of 103 dB for best speech performance
Signal-to-noise ratio of 67 dBSPL
<1% total harmonic distortions up to high SPL levels
Acoustic overload point at 130 dBSPL
Increased operating temperature range: TA = -40°C …105 °C
Digital PDM output
Automotive qualification according to AEC-Q103-003

Note: More technical information can be found in the IM67D130A product brief linked at the bottom of this page and on the product page of IM67D130A XENSIV MEMS Microphone.