Gun type recognition from gunshot audio recordings
- 1 March 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
This paper describes an extension of an intelligent acoustic event detection system, which is able to recognize sounds of dangerous events such as breaking glass or gunshot sounds in urban environment from commonly used noise monitoring stations. We propose to extend the system the way that it would not only detect the gunshots, but it would identify a suspects gun/pistol type as well. Such extension could help the investigation process and the suspect identification. The proposed extension provides a new functionality of the gun type recognition (classification) based on audio recordings captured. This research topic is discussed in other research papers marginally. Different kinds of features were extracted for this challenging task and feature vectors were reduced by using mutual information based feature selection algorithms. The proposed system uses two phase selection process, HMM (Hidden Markov Model) classification and Viterbi based decoding algorithm. The presented approach reached promising results in the experiments (higher than 80% of ACC and TPR).Keywords
This publication has 13 references indexed in Scilit:
- EAR-TUKE: The Acoustic Event Detection SystemCommunications in Computer and Information Science, 2014
- The Classification of Gun’s Type Using Image Recognition TheoryInternational Journal of Information and Electronics Engineering, 2014
- Linear Feature Transformations in Slovak Phoneme-Based Continuous Speech Recognition2012
- Filter Methods for Feature Selection – A Comparative Study2007
- Audio analysis for surveillance applications2006
- Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Detection Theory2004
- Minimum redundancy feature selection from microarray gene expression data2004
- Application of the mutual information criterion for feature selection in computer‐aided diagnosisMedical Physics, 2001
- Wrappers for feature subset selectionArtificial Intelligence, 1997