Optimizing Violence Detection in Video Classification Accuracy through 3D Convolutional Neural Networks

TL;DR

This study investigates how analyzing a specific number of frames in a 3D CNN affects violence detection accuracy in videos, finding that three frames optimize performance.

Contribution

It introduces a method to determine the optimal number of frames for violence detection using 3D CNNs, improving accuracy in video classification tasks.

Findings

Maximum validation accuracy of 94.87% with three frames analyzed at a time

Analyzing three frames yields better results than one, two, ten, or twenty frames

Methodology can be applied to other complex video classification problems

Abstract

As violent crimes continue to happen, it becomes necessary to have security cameras that can rapidly identify moments of violence with excellent accuracy. The purpose of this study is to identify how many frames should be analyzed at a time in order to optimize a violence detection model's accuracy as a parameter of the depth of a 3D convolutional network. Previous violence classification models have been created, but their application to live footage may be flawed. In this project, a convolutional neural network was created to analyze optical flow frames of each video. The number of frames analyzed at a time would vary with one, two, three, ten, and twenty frames, and each model would be trained for 20 epochs. The greatest validation accuracy was 94.87% and occurred with the model that analyzed three frames at a time. This means that machine learning models to detect violence may function better when analyzing three frames at a time for this dataset. The methodology used to identify the optimal number of frames to analyze at a time could be used in other applications of video classification, especially those of complex or abstract actions, such as violence.