System for Acoustic Detection |
|---|
| Jakub Svatos, Jan Belak, Jan Holub |
- Abstract:
- At present, acoustic detection techniques of gunshots (gunshot detection) are increasingly being used not only for military applications but also for civilian purposes. Detection, localization, and classification of gunshots employing acoustic detection is perspective alternative to visual detection, which is commonly used. In certain situations, to detect a source of a gunshot, an automatic acoustic detection system may be preferable. This paper presents a system for acoustic detection, which can detect localize and classify acoustic events such as gunshots. Tested firearms are 9 mm short gun, 6.35 mm short gun, .22 short gun, and .22 rifle gun with various subsonic and supersonic ammunition. As false alarms, sets of different impulse acoustic events like door slams, breaking glass, etc. have been used. To successfully classify the tested acoustic signals, Continuous Wavelet and Mel Frequency Transformation methods have been used for the signal processing, and the fully twolayer connected neural network has been implemented. The results show that the acoustic detector can be used for reliable gunshot detection, localization, and classification.
- Download:
- IMEKO-TC4-2020-65.pdf
- DOI:
- -