A shallow 3D convolutional neural network for violence detection in videos
With the recent worldwide statistical rise in the amount of public violence, automated violence detection in surveillance cameras has become a matter of high importance. This work introduces an end-to-end, trainable 3D Convolutional Neural Network (3D CNN) for detecting violence in video footage. Th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-06-01
|
| Series: | Egyptian Informatics Journal |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110866524000185 |
| _version_ | 1827212058668564480 |
|---|---|
| author | Naz Dündar Ali Seydi Keçeli Aydın Kaya Hayri Sever |
| author_facet | Naz Dündar Ali Seydi Keçeli Aydın Kaya Hayri Sever |
| author_sort | Naz Dündar |
| collection | DOAJ |
| description | With the recent worldwide statistical rise in the amount of public violence, automated violence detection in surveillance cameras has become a matter of high importance. This work introduces an end-to-end, trainable 3D Convolutional Neural Network (3D CNN) for detecting violence in video footage. The proposed network is inherently capable of processing both spatial and temporal information, thereby obviating the need for additional models that would introduce higher computational requirements and complexity. This work has two main contributions: 1) developing a lightweight 3D CNN suitable for inference on edge devices as mobile systems, and 2) a comprehensive explanation of all components comprising a CNN model, thereby enhances model interpretability. Experiments were conducted to assess the performance of the proposed model using a consolidated dataset combining four benchmark datasets. The results of the experiments support the asserted contributions, which are discussed in detail. |
| first_indexed | 2024-04-24T20:13:33Z |
| format | Article |
| id | doaj.art-c86a45b759b54c26af8b3bd727315846 |
| institution | Directory Open Access Journal |
| issn | 1110-8665 |
| language | English |
| last_indexed | 2025-03-21T13:53:30Z |
| publishDate | 2024-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Egyptian Informatics Journal |
| spelling | doaj.art-c86a45b759b54c26af8b3bd7273158462024-06-26T05:24:36ZengElsevierEgyptian Informatics Journal1110-86652024-06-0126100455A shallow 3D convolutional neural network for violence detection in videosNaz Dündar0Ali Seydi Keçeli1Aydın Kaya2Hayri Sever3Department of Software Engineering, Çankaya University, Türkiye; Corresponding author.Department of Computer Engineering, Hacettepe University, TürkiyeDepartment of Computer Engineering, Hacettepe University, TürkiyeDepartment of Computer Engineering, Çankaya University, TürkiyeWith the recent worldwide statistical rise in the amount of public violence, automated violence detection in surveillance cameras has become a matter of high importance. This work introduces an end-to-end, trainable 3D Convolutional Neural Network (3D CNN) for detecting violence in video footage. The proposed network is inherently capable of processing both spatial and temporal information, thereby obviating the need for additional models that would introduce higher computational requirements and complexity. This work has two main contributions: 1) developing a lightweight 3D CNN suitable for inference on edge devices as mobile systems, and 2) a comprehensive explanation of all components comprising a CNN model, thereby enhances model interpretability. Experiments were conducted to assess the performance of the proposed model using a consolidated dataset combining four benchmark datasets. The results of the experiments support the asserted contributions, which are discussed in detail.http://www.sciencedirect.com/science/article/pii/S1110866524000185 |
| spellingShingle | Naz Dündar Ali Seydi Keçeli Aydın Kaya Hayri Sever A shallow 3D convolutional neural network for violence detection in videos Egyptian Informatics Journal |
| title | A shallow 3D convolutional neural network for violence detection in videos |
| title_full | A shallow 3D convolutional neural network for violence detection in videos |
| title_fullStr | A shallow 3D convolutional neural network for violence detection in videos |
| title_full_unstemmed | A shallow 3D convolutional neural network for violence detection in videos |
| title_short | A shallow 3D convolutional neural network for violence detection in videos |
| title_sort | shallow 3d convolutional neural network for violence detection in videos |
| url | http://www.sciencedirect.com/science/article/pii/S1110866524000185 |
| work_keys_str_mv | AT nazdundar ashallow3dconvolutionalneuralnetworkforviolencedetectioninvideos AT aliseydikeceli ashallow3dconvolutionalneuralnetworkforviolencedetectioninvideos AT aydınkaya ashallow3dconvolutionalneuralnetworkforviolencedetectioninvideos AT hayrisever ashallow3dconvolutionalneuralnetworkforviolencedetectioninvideos AT nazdundar shallow3dconvolutionalneuralnetworkforviolencedetectioninvideos AT aliseydikeceli shallow3dconvolutionalneuralnetworkforviolencedetectioninvideos AT aydınkaya shallow3dconvolutionalneuralnetworkforviolencedetectioninvideos AT hayrisever shallow3dconvolutionalneuralnetworkforviolencedetectioninvideos |