A Gunshot Recognition Method Based on Multi-Scale Spectrum Shift Module
A Gunshot Recognition Method Based on Multi-Scale Spectrum Shift Module
复制标题
一种基于多尺度谱平移模块的枪声识别方法
DOI：
10.3390/electronics11233859
复制
发表时间：
2022-11
期刊：
影响因子：
2.9
通讯作者：
Jibin Xu
中科院分区：
文献类型：
--
作者：
Jian Li;Jinming Guo;Mingxing Ma;Yuan Zeng;Chuankun Li;Jibin Xu
针对目前枪声识别网络存在网络模型较大、识别精度较低等问题，提出一种基于多尺度谱移模块的神经网络，以充分挖掘枪声谱间的相关信息。该网络采用密集连接的卷积网络结构，在分支上采用多尺度谱移模块实现频谱信息的交互。这种谱移代替了谱间的欠采样操作，实现了谱的全局化特征提取，避免了欠采样过程中的信息损失，进一步提高了谱特征图的质量。实验基于NIJ Grant 2016-DN-BX-0183枪击数据集和YouTube公开的枪击数据集进行，两者的分类准确率分别达到83.2%和95.1%，网络模型大小控制在16 MB左右。实验结果表明，与现有的其他卷积神经网络方法相比，该网络能更好地挖掘全局时频信息，具有更高的枪声识别准确率。
In view of the issues such as the larger network model and lower recognition accuracy of the current gunshot recognition networks, a neural network based on a multi-scale spectrum shift module is proposed in this paper to fully mine the relevant information among the gunshot spectrums. This network employs the architecture of a densely connected convolutional network and uses a multi-scale spectrum shift module on the branch to realize the interaction among spectrum information. This spectrum shift replaces the under-sampling operation among the spectrums, realizes the globalized feature extraction of the spectrum, avoids the loss of information during the under-sampling process, and further improves the quality of the spectrum feature map. Experiments were conducted based on the NIJ Grant 2016-DN-BX-0183 gunshot dataset and YouTube dataset on gunshots that have been open to the public, both of whose classification accuracy reached 83.2% and 95.1%, respectively, with the size of the network model being controlled at around 16 MB. The experimental results indicate that, compared with other existing methods for convolutional neural network, the proposed network can mine globalized time-frequency information better and effectively, and has a higher accuracy of gunshot recognition.
登录
查看更多内容
影响因子：
1.4
作者：
J. R. Aguilar
通讯作者：
J. R. Aguilar
影响因子：
2.4
作者：
D. Hawthorne;W. Horn;D. Reinke
通讯作者：
D. Hawthorne;W. Horn;D. Reinke
DOI：
10.1109/taslp.2017.2690579
发表时间：
2017-06
期刊：
IEEE/ACM Transactions on Audio, Speech, and Language Processing
影响因子：
--
作者：
Héctor A. Sánchez-Hevia;D. Ayllón;R. Gil-Pita;M. Rosa-Zurera
通讯作者：
Héctor A. Sánchez-Hevia;D. Ayllón;R. Gil-Pita;M. Rosa-Zurera
DOI：
--
发表时间：
2021
期刊：
--
影响因子：
--
作者：
Araştırma Makalesi;Adıyaman Üniversitesi;M. Dergisi;T. Tuncer;S. Dogan;Erhan Akbal;Emrah Aydemir
通讯作者：
Araştırma Makalesi;Adıyaman Üniversitesi;M. Dergisi;T. Tuncer;S. Dogan;Erhan Akbal;Emrah Aydemir
影响因子：
2.9
作者：
M. Djeddou;Tayeb Touhami
通讯作者：
M. Djeddou;Tayeb Touhami