Seeing with Sound: AI-Based Detection of Participants in Automotive Environment from Passive Audio

The use of passive audio to detect road participants using low-cost, automotive-qualified hardware.


Existing ADAS solutions for car environmental awareness (cameras, LiDAR, ultrasonic, etc.) require targets to be in a clear line of sight from the sensor. The target must be illuminated by some source of energy, so systems are affected by dust, weather, lighting, and obstacles. We address those limitations using a passive acoustic solution that “listens” to the environment. It can hear potential targets around corners or out of sight over a distance, providing early warning that supplements and improves other ADAS systems. We aim to detect a variety of road participants including sirens, approaching vehicles, bicycles, and even pedestrians. We discuss use cases and challenges, present an inexpensive reference architecture based on automotive grade components, and report on the updated state of development with initial validation results.

Find more information here.

Fig.1: Processing flow diagram for Renesas Reality AI SWS system.

Leave a Reply

(Note: This name will be displayed publicly)