August 7, 2025Open Access

Real-Time Sound Source Localization Method Based on Selective SRP-PHAT and Vision Fusion

Key Points

MAIN FINDING: The proposed method enhances sound source localization accuracy to ±5 degrees using vision fusion and selective SRP-PHAT.
KEY EVIDENCE: Experimental results demonstrate a processing speed exceeding 10 FPS in real-world environments, outperforming traditional scanning methods.
APPROACH: The method integrates face detection and intelligent orientation selection to guide the scanning process and classify sound sources.
SIGNIFICANCE: This advancement addresses computational complexity issues, enabling effective real-time localization in noisy settings.

Abstract

Aiming at the problem that the traditional SRP-PHAT sound source localization method performs intensive search in a 360-degree space, resulting in high computational complexity and difficulty in meeting real-time requirements, an innovative high-precision sound source localization method is proposed. This method combines the selective SRP-PHAT algorithm with real-time visual analysis. Its core innovations include using face detection to dynamically determine the scanning angle range to achieve visually guided selective scanning, distinguishing face sound sources from background noise through a sound source classification mechanism, and implementing intelligent background orientation selection to ensure comprehensive monitoring of environmental noise. Experimental results show that the method achieves a positioning accuracy of ±5 degrees and a processing speed of more than 10FPS in complex real environments, and its performance is significantly better than the traditional full-angle scanning method.

Read Full Paperexternally

Mark Helpful

Bookmark

Relay

View Full Paper