Deep Spectrogram Learning for Gunshot Classification: A Comparative Study of CNN Architectures and Time-Frequency Representations

Сохранить в:

Библиографические подробности
Опубликовано в::	Journal of Imaging vol. 11, no. 8 (2025), p. 281-307
Главный автор:	Pafan, Doungpaisan
Другие авторы:	Peerapol, Khunarsa
Опубликовано:	MDPI AG
Предметы:	United States > US Accuracy Datasets Deep learning Wavelet transforms Law enforcement Color imagery Racial profiling Artificial neural networks Audio recordings Public safety Small arms Computer vision Automation Machine learning Image processing Representations Pattern recognition Sound Comparative studies Artificial intelligence Fourier transforms Spectrograms Time-frequency analysis Neural networks Classification Image classification Surveillance Gun violence Acoustics Murders & murder attempts Surveillance systems
Online-ссылка:	Citation/Abstract Full Text + Graphics Full Text - PDF
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!

Описание
Краткий обзор:	Gunshot sound classification plays a crucial role in public safety, forensic investigations, and intelligent surveillance systems. This study evaluates the performance of deep learning models in classifying firearm sounds by analyzing twelve time–frequency spectrogram representations, including Mel, Bark, MFCC, CQT, Cochleagram, STFT, FFT, Reassigned, Chroma, Spectral Contrast, and Wavelet. The dataset consists of 2148 gunshot recordings from four firearm types, collected in a semi-controlled outdoor environment under multi-orientation conditions. To leverage advanced computer vision techniques, all spectrograms were converted into RGB images using perceptually informed colormaps. This enabled the application of image processing approaches and fine-tuning of pre-trained Convolutional Neural Networks (CNNs) originally developed for natural image classification. Six CNN architectures—ResNet18, ResNet50, ResNet101, GoogLeNet, Inception-v3, and InceptionResNetV2—were trained on these spectrogram images. Experimental results indicate that CQT, Cochleagram, and Mel spectrograms consistently achieved high classification accuracy, exceeding 94% when paired with deep CNNs such as ResNet101 and InceptionResNetV2. These findings demonstrate that transforming time–frequency features into RGB images not only facilitates the use of image-based processing but also allows deep models to capture rich spectral–temporal patterns, providing a robust framework for accurate firearm sound classification.
ISSN:	2313-433X
DOI:	10.3390/jimaging11080281
Источник:	Advanced Technologies & Aerospace Database