2D bidirectional gated recurrent unit convolutional Neural networks for end-to-end violence detection In videos
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910601262923776 |
|---|---|
| author | Traoré, Abdarahmane Akhloufi, Moulay A. |
| author_facet | Traoré, Abdarahmane Akhloufi, Moulay A. |
| contents | Abnormal behavior detection, action recognition, fight and violence detection in videos is an area that has attracted a lot of interest in recent years. In this work, we propose an architecture that combines a Bidirectional Gated Recurrent Unit (BiGRU) and a 2D Convolutional Neural Network (CNN) to detect violence in video sequences. A CNN is used to extract spatial characteristics from each frame, while the BiGRU extracts temporal and local motion characteristics using CNN extracted features from multiple frames. The proposed end-to-end deep learning network is tested in three public datasets with varying scene complexities. The proposed network achieves accuracies up to 98%. The obtained results are promising and show the performance of the proposed end-to-end approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07588 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 2D bidirectional gated recurrent unit convolutional Neural networks for end-to-end violence detection In videos Traoré, Abdarahmane Akhloufi, Moulay A. Computer Vision and Pattern Recognition Abnormal behavior detection, action recognition, fight and violence detection in videos is an area that has attracted a lot of interest in recent years. In this work, we propose an architecture that combines a Bidirectional Gated Recurrent Unit (BiGRU) and a 2D Convolutional Neural Network (CNN) to detect violence in video sequences. A CNN is used to extract spatial characteristics from each frame, while the BiGRU extracts temporal and local motion characteristics using CNN extracted features from multiple frames. The proposed end-to-end deep learning network is tested in three public datasets with varying scene complexities. The proposed network achieves accuracies up to 98%. The obtained results are promising and show the performance of the proposed end-to-end approach. |
| title | 2D bidirectional gated recurrent unit convolutional Neural networks for end-to-end violence detection In videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.07588 |