Two-stream Multi-dimensional Convolutional Network for Real-time Violence Detection

TL;DR

This paper introduces a lightweight two-stream multi-dimensional convolutional network that effectively combines RGB frames and optical flow for real-time violence detection, achieving state-of-the-art accuracy with reduced complexity.

Contribution

The novel 2s-MDCN architecture efficiently extracts spatial and temporal features using multi-dimensional convolutions, improving accuracy while maintaining low computational cost.

Findings

Achieved 89.7% accuracy on a large violence detection dataset.

RGB and optical flow combination improves accuracy by 2.2%.

Models are lightweight and suitable for real-time surveillance applications.

Abstract

The increasing number of surveillance cameras and security concerns have made automatic violent activity detection from surveillance footage an active area for research. Modern deep learning methods have achieved good accuracy in violence detection and proved to be successful because of their applicability in intelligent surveillance systems. However, the models are computationally expensive and large in size because of their inefficient methods for feature extraction. This work presents a novel architecture for violence detection called Two-stream Multi-dimensional Convolutional Network (2s-MDCN), which uses RGB frames and optical flow to detect violence. Our proposed method extracts temporal and spatial information independently by 1D, 2D, and 3D convolutions. Despite combining multi-dimensional convolutional networks, our models are lightweight and efficient due to reduced channel capacity, yet they learn to extract meaningful spatial and temporal information. Additionally, combining RGB frames and optical flow yields 2.2% more accuracy than a single RGB stream. Regardless of having less complexity, our models obtained state-of-the-art accuracy of 89.7% on the largest violence detection benchmark dataset.