2D bidirectional gated recurrent unit convolutional Neural networks for end-to-end violence detection In videos

TL;DR

This paper introduces an end-to-end deep learning architecture combining 2D CNNs and BiGRUs for violence detection in videos, achieving high accuracy across multiple datasets.

Contribution

It presents a novel combination of CNN and BiGRU for simultaneous spatial and temporal feature extraction in violence detection.

Findings

Achieves up to 98% accuracy on public datasets.

Effective in varying scene complexities.

Demonstrates promising performance of the end-to-end model.

Abstract

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.