Unmanned aerial vehicle sound source positioning method and system based on microphone array and artificial intelligence
By combining microphone arrays and artificial intelligence to locate sound sources, the problem of noise sensitivity and insufficient positioning accuracy of existing acoustic detection methods in complex environments has been solved, realizing high-precision drone detection and tracking, which is suitable for multi-scenario prevention and control.
Patent Information
- Application Number
- CN202610531534.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-21
- Publication Date
- 2026-07-17
AI Technical Summary
Existing acoustic detection methods are sensitive to environmental noise, have low positioning accuracy, and lack model generalization ability, making it difficult to efficiently and reliably detect and identify drones in complex environments.
A sound source localization method based on microphone array and artificial intelligence is adopted. Sound signals are collected by a four-channel microphone array, and sound feature recognition is performed by combining the ECAPA-TDNN model and the SELDnet model for localization, so as to achieve high-precision sound source localization of UAVs.
It achieves high-precision drone detection and tracking in complex environments, with strong model adaptability, reducing false alarms and missed alarms, and is suitable for multi-scenario prevention and control.
Smart Images
Figure CN122417073A_ABST