A Sound Source Localization Method under NLOS Environment for Vehicles

Current perception systems may be hard to detect other road users at the occluded scene, which may lead to incidents. We propose a method that can localize sound sources emitted by the engine of a vehicle under a Non-Line-Of-Sight (NLOS) environment. This method transforms the uniform moving sound source localization problem into the solution of an equation set that consists of the theory of sound diffraction, Doppler shift, and geometric location, and then we use a multi-sensor fusion algorithm to reduce the error, which improves the real-time performance of localization. Finally, our approach can realize vehicle location positioning in NLOS scenarios with four microphones and increase driver safety. The effectiveness of the proposed method is validated by simulation based on the finite element method.