Real-Time Sound Source Localization Using Intensity Variations Muhammad

This paper presents a real-time method for sound source localization using a multi-channel sensor array and intensity-based weighted averaging. The system employs six analog sound sensors arranged in a circular configuration, each positioned at predetermined angles. Sound intensities from each sensor are captured, summed over time, and processed using a weighted average approach to estimate the direction of the sound source. By leveraging the relative strengths of the signals detected by the sensors, the system calculates a resultant angle that accurately represents the sound's direction. The proposed method focuses on intensity variations, making it both computationally efficient and well-suited for low-power devices such as microcontrollers. The performance of the system is evaluated in real-time using embedded hardware, demonstrating its applicability in various environments, such as robotics. This paper highlights the simplicity and effectiveness of using intensity-based sound localization with an average error of just over 5°, and the percentage error remained below 3% for most positions.