Gunshot Sound Measurement and Analysis

Tardif, Bruno; Lo, David; Goubran, Rafik

doi:10.1109/sas51076.2021.9530145

Cited by 5 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…T HE field of audio forensics has seen significant advancements in recent years to identify and analyze gunshot sounds through gunfire recognition techniques [1]. With rising gun-related crimes globally, it is vital to accurately distinguish firearm noises from other sounds within the recorded audio, aiding corporate companies in tackling heightened security challenges [2]. Digital signal processing (DSP), pattern recognition (PR), and machine learning (ML) techniques are utilized in the classification process thus al-lowing effective distinction among different firearm sounds.…”

Section: Introductionmentioning

confidence: 99%

Preventing Crimes Through Gunshots Recognition Using Novel Feature Engineering and Meta-Learning Approach

Raza,

Rustam,

Mallampati

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Gunshot sounds are common in crimes, particularly those involving threats, harassment, or killing. The gunshot sounds in crimes can create fear and panic among victims, often leading to psychological trauma. Gunshot sounds are associated with a significant mortality rate, especially in cases of gun violence. The sound of gunshots can serve as evidence in criminal investigations, allowing law enforcement officials to determine the number of shots fired, the caliber of the gun used, and the distance from which the shots were fired. Efficient gunshot detection is necessary to address the issue of gun violence in society. This study aims to detect gunshot sounds using an efficient approach to prevent crimes. The frequency-time domain spectrum analysis is performed to understand the patterns of signals related to each target class. A novel Discrete Wavelet Transform Random Forest Probabilistic (DWT-RFP) feature engineering approach is proposed, which takes Mel-frequency cepstral coefficients (MFCC) extracted from gunshot sound data as input for feature extraction. A novel meta-learning-based Meta-RF-KN (MRK) is proposed to detect gunshots based on newly created ensemble features with a DWT-RFP approach. For experiments, the gunshot sounds dataset containing 851 audio clips collected from public videos on YouTube from eight kinds of gun models, is used. Advanced machine learning and deep learning techniques are applied in comparison to evaluate the performance of the proposed approach. Extensive experiments show that the proposed MRK approach achieves 99% k-fold accuracy for detecting gunshots and outperforms state-of-the-art approaches. The proposed approach can potentially be used for accurate gunshot detection and to help prevent crimes.

show abstract

Section: Introductionmentioning

confidence: 99%

Preventing Crimes Through Gunshots Recognition Using Novel Feature Engineering and Meta-Learning Approach

Raza,

Rustam,

Mallampati

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The first contribution is a method for accurately measuring impulse gunshot sounds using a grid of pressure microphones and a high-speed acquisition system. This contribution has been published in the following paper [1]:…”

Section: Contributionsmentioning

confidence: 99%

Gunshots Sound Analysis, Identification, and Impact on Hearing

Tardif¹

View full text Add to dashboard Cite

Analyzing the sound resulting from a gunshot can help identify the type of gun used. This can help determine the appropriate public safety actions when a gunshot sound is detected in a public space. Furthermore, analyzing the sound can lead to a better understanding of the impact of this sound on hearing. For example, exposure to gunshot sounds can cause hearing impairments. Measuring these sounds from various locations and analyzing them can improve the design of hearing protectors and help enact regulations to minimize the impact of gunshot sounds on hearing impairments.In this thesis, acoustic data was collected from different guns and a mortar for analysis. To capture their sound including any non-symmetric sound propagation from the gunshots, 27 high dynamic range pressure 1/8" microphones were placed around the weapons forming a polar grid pattern. Audio signals from all microphones were captured at 204.8 kHz sampling rate synchronously to preserve the fidelity of the impulse nature of the gunshots. This thesis entails two types of analysis. The first is an image-based analysis method to take advantage of the recent advancement of image recognition techniques. In this thesis, we used Continuous Wavelet Transform (CWT) and Short-Time Fourier Transform (STFT) to obtain the time-frequency spectrogram of the gunshot recordings as images. We then employed a two-stage machine-learning classifier to process the images to identify the specific gun or mortar the gunshot was originated from. Classification accuracy of 98.1% was achieved in this example. A second type of analysis was conducted using a novel method for characterizing acoustic attenuation properties that respects the iii spectral sensitivity of the human ear and preserves the energy in its octave bands at the same time.

show abstract

Gun identification from gunshot audios for secure public places using transformer learning

Nijhawan

Ansari

Kumar

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Increased mass shootings and terrorist activities severely impact society mentally and physically. Development of real-time and cost-effective automated weapon detection systems increases a sense of safety in public. Most of the previously proposed methods were vision-based. They visually analyze the presence of a gun in a camera frame. This research focuses on gun-type (rifle, handgun, none) detection based on the audio of its shot. Mel-frequency-based audio features have been used. We compared both convolution-based and fully self-attention-based (transformers) architectures. We found transformer architecture generalizes better on audio features. Experimental results using the proposed transformer methodology on audio clips of gunshots show classification accuracy of 93.87%, with training loss and validation loss of 0.2509 and 0.1991, respectively. Based on experiments, we are convinced that our model can effectively be used as both a standalone system and in association with visual gun-detection systems for better security.

show abstract

Gunshot Sound Measurement and Analysis

Cited by 5 publications

References 23 publications

Preventing Crimes Through Gunshots Recognition Using Novel Feature Engineering and Meta-Learning Approach

Preventing Crimes Through Gunshots Recognition Using Novel Feature Engineering and Meta-Learning Approach

Gunshots Sound Analysis, Identification, and Impact on Hearing

Gun identification from gunshot audios for secure public places using transformer learning

Contact Info

Product

Resources

About