Algorithm for Gunshot Detection Using Mel-Frequency Cepstrum Coefficients (MFCC)

Suman, Preetam; Karan, Subhdeep; Singh, Vrijendra; Maringanti, R.

doi:10.1007/978-81-322-1823-4_15

Cited by 9 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, Suman [28] also tested MFCC and three layer Artificial Neural Networks (ANN) classifier achieving 95 % for clean and 85 % for noisy recordings. As we can see, our system is comparable with other systems described in the relevant papers using inexpensive and easy to deploy components (common outdoor microphone or existing noise monitoring stations could be used).…”

Section: Resultsmentioning

confidence: 99%

“…Detection, classification and localization (using Acoustic Vector Sensor) could be done in separate modules as it is described in [16,17]. There have been similar gunshot detection systems already presented in the papers based on MFCC, LPC (Linear Prediction Coefficients) & HMM [7], GMM with MPEG-7 and MFCC feature vector reduced using floating search vector feature selection method [8] and [30], pitch range (PR) of non-speech sounds and the Autocorrelation Function using Support Vector Machines (SVM) with Gaussian kernel and Radial Basis Function Neural Network classifiers [29] and recently MFCC and three layer Artificial Neural Networks (ANN) classifier [28]. Their detection results are discussed and compared in the conclusion section.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient acoustic detector of gunshots and glass breaking

Lojka

Pleva

Kiktová

et al. 2015

Multimed Tools Appl

View full text Add to dashboard Cite

An efficient acoustic events detection system EAR-TUKE is presented in this paper. The system is capable of processing continuous input audio stream in order to detect potentially dangerous acoustic events, specifically gunshots or breaking glass. The system is programmed entirely in C++ language (core math. functions in C) and was designed to be self sufficient without requiring additional dependencies. In the design and development process the main focus was put on easy support of new acoustic events detection, low memory profile, low computational requirements to operate on devices with low resources, and on long-term operation and continuous input stream monitoring without any maintenance. In order to satisfy these requirements on the system, EAR-TUKE is based on a custom approach to detection and classification of acoustic events. The system is using acoustic models of events based on Hidden Markov Models (HMMs) and a modified Viterbi decoding process with an additional module to allow continuous monitoring. Cepstral Mean Normalization (CMN) and our proposed removal of basic coefficients from feature vectors to increase robustness. This paper also presents the development process and results evaluating the final design of the system.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Efficient acoustic detector of gunshots and glass breaking

Lojka

Pleva

Kiktová

et al. 2015

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…The motivation of this work stems from the fact that datasets containing sounds closely related to gunshot sounds are not readily available for research purposes. Although a great amount of work has been presented in the detection of gunshot sounds [3][4][5][6][7][8][9][10][11][12][13][14][15][16], comparative analyses of similar audio events are not as detailed, though in the literature, researchers carried out comparative analyses of similar sounding events to gunshot audio events with abrupt changes in energy, such as door slams, claps, and firecrackers [10][11][12][13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

“…The work in [16] provided the comparison of impulsive sounds which includes the explosion of a balloon, clap and the sound of plosive consonants such a [p], [t], and [k]. The authors of [10][11][12][13][14][15][16] all discuss the detection of gunshot sounds in comparison to other sounds; however, they did not provide a database of the non-gunshot sounds readily available for further research.…”

Section: Introductionmentioning

confidence: 99%

Data Collection, Modeling, and Classification for Gunshot and Gunshot-like Audio Events: A Case Study

Singh

Zhuang

Pawani

2021

Sensors

View full text Add to dashboard Cite

Distinguishing between a dangerous audio event like a gun firing and other non-life-threatening events, such as a plastic bag bursting, can mean the difference between life and death and, therefore, the necessary and unnecessary deployment of public safety personnel. Sounds generated by plastic bag explosions are often confused with real gunshot sounds, by either humans or computer algorithms. As a case study, the research reported in this paper offers insight into sounds of plastic bag explosions and gunshots. An experimental study in this research reveals that a deep learning-based classification model trained with a popular urban sound dataset containing gunshot sounds cannot distinguish plastic bag pop sounds from gunshot sounds. This study further shows that the same deep learning model, if trained with a dataset containing plastic pop sounds, can effectively detect the non-life-threatening sounds. For this purpose, first, a collection of plastic bag-popping sounds was recorded in different environments with varying parameters, such as plastic bag size and distance from the recording microphones. The audio clips’ duration ranged from 400 ms to 600 ms. This collection of data was then used, together with a gunshot sound dataset, to train a classification model based on a convolutional neural network (CNN) to differentiate life-threatening gunshot events from non-life-threatening plastic bag explosion events. A comparison between two feature extraction methods, the Mel-frequency cepstral coefficients (MFCC) and Mel-spectrograms, was also done. Experimental studies conducted in this research show that once the plastic bag pop sounds are injected into model training, the CNN classification model performs well in distinguishing actual gunshot sounds from plastic bag sounds.

show abstract

“…Silah sesi sınıflandırmak için MFCC ile LPC öznitelikleri, çaprazkorelasyon ve SVM sınıflandırıcı kullanılan çalışmada, farklı atış mesafelerinden G3 ve MP5 silahlar ile elde edilen 332 atış ve 102 yabancı ses kaydı kullanılmış, LPC ve çaprazkorelasyon ile Destek Vektör Makineleri (SVM -Support Vektor Machine) sınıflandırıcıda %99.7'lik bir doğru sınıflandırmaya ulaşılmıştır [2]. Suman vd., 150 silah sesi ile MFCC ve üç katmanlı Yapay Sinir Ağları (YSA) sınıflandırıcı ile gürültüsüz ortamda %95 ve gürültülü ortamda %85 başarı elde etmiştir [18].…”

Section: Gi̇ri̇ş (Introduction)unclassified

Silah Sesleri Kullanılarak Ateşli Silahların Sınıflandırılmasında Akustik Parametrelerin Etkisi

Özseven¹,

Düğenci²

2018

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım Ve Teknoloji

View full text Add to dashboard Cite

Makale Bilgisi ÖzAkustik analiz özellikle malzeme bilimi ve insan seslerinde kullanılmakta olup son yıllarda savunma sanayiinde ses perdesi, silah ve nişancı tespiti, insansız hava araçları gibi bir çok alanda kullanılmaktadır. Ateşli silahlarla ilgili eylemler hem güvenlik güçleri hem de halk için artan bir endişe kaynağıdır. Silah seslerinin sınıflandırılması için ticari veya deneysel çeşitli çalışmalar mevcuttur. Bu çalışmanın amacı silah seslerini kullanarak ateşli silahların türünü tespit etmede akustik analizin etkilerinin incelenmesidir. Çalışmada 23 ateşli silaha ait 510 atış ses kaydı kullanılmıştır. Akustik analiz için formant frekansları, MFCC, LPCC ve enerji parametreleri incelenmiştir. Akustik parametrelerin silahları sınıflandırmadaki etkinliği istatistiksel olarak analiz edilmiş ve kullanılan tüm parametrelerin etkili olduğu görülmüştür. MLP sınıflandırıcı ile sınıflandırma performansı test edilmiş ve ateşli silah tanıma oranı %71.56 elde edilmiştir. Tanıma oranı en yüksek silah türü "Carl Gustav M45" ve "Tokarev PPSh", tanıma oranı en düşük olan silah "Tikka Model T2" olarak tespit edilmiştir. The Impact of Acoustic Parameters on the Classification of Firearms Using Gunshots AbstractAcoustic analysis is mainly used in material science and human voice. In recent years, many areas such as sound perception, gun and shooter detection, unmanned aerial vehicles have been used in the defense industry. Actions related to firearms are an increasing source of concern for both security forces and the public. There are various commercial or experimental studies for the classification of gunshots. The purpose of this study is to examine the effects of acoustic analysis on the detection of firearms by using gunshots. In the study, 511 gunshots recordings of 23 firearms were used. The formant frequencies, MFCC, LPCC and energy parameters for acoustic analysis are examined. The effectiveness of the acoustic parameters in classifying the weapons was analyzed statistically and all the parameters used were found to be effective. The classification performance was tested with the MLP classifier and the firearm recognition rate was 71.56%. The "Carl Gustav M45-b" and "Tokarev PPSh" was identified as the weapon with the highest recognition rate and the lowest "Tikka Model T3" recognition rate.

show abstract

Algorithm for Gunshot Detection Using Mel-Frequency Cepstrum Coefficients (MFCC)

Cited by 9 publications

References 6 publications

Efficient acoustic detector of gunshots and glass breaking

Efficient acoustic detector of gunshots and glass breaking

Data Collection, Modeling, and Classification for Gunshot and Gunshot-like Audio Events: A Case Study

Silah Sesleri Kullanılarak Ateşli Silahların Sınıflandırılmasında Akustik Parametrelerin Etkisi

Contact Info

Product

Resources

About