Deep Spectrogram Learning for Gunshot Classification: A Comparative Study of CNN Architectures and Time-Frequency Representations
Journal of Imaging · 21.08.2025 · 11 (8) · 281
DOI: 10.3390/jimaging11080281 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 21.08.2025. Verfasst von Pafan Doungpaisan und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Industrial Technology and Management, King Mongkut's University of Technology North Bangkok, Bangkok 10800, Thailand. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Industrial Technology and Management, King Mongkut's University of Technology North Bangkok, Bangkok 10800, Thailand.
- Faculty of Science and Technology, Uttaradit Rajabhat University, Uttaradit 53000, Thailand.
ORCID-Profile: Pafan Doungpaisan, Peerapol Khunarsa
Zitieren
APA
Doungpaisan, P., & Khunarsa, P. (2025). Deep Spectrogram Learning for Gunshot Classification: A Comparative Study of CNN Architectures and Time-Frequency Representations. Journal of Imaging, 11(8), 281. https://doi.org/10.3390/jimaging11080281
Vancouver
Doungpaisan P, Khunarsa P. Deep Spectrogram Learning for Gunshot Classification: A Comparative Study of CNN Architectures and Time-Frequency Representations. Journal of Imaging. 2025;11(8):281. doi:10.3390/jimaging11080281
BibTeX
@article{Doungpaisan2025,
author = {Doungpaisan, Pafan and Khunarsa, Peerapol},
title = {Deep Spectrogram Learning for Gunshot Classification: A Comparative Study of CNN Architectures and Time-Frequency Representations},
journal = {Journal of Imaging},
year = {2025},
volume = {11},
number = {8},
pages = {281},
doi = {10.3390/jimaging11080281}
}
EUVIMED