A Hybrid Deep Learning Approach for Violence Detection in Videos Video G r nt lerinde Siddet I eren Sahnelerin Tespiti i in Hibrit bir Derin grenme Yaklasimi

AKBAŞ A., ÜÇGÜN H., Ali A. A.

2025 Innovations in Intelligent Systems and Applications Conference, ASYU 2025, Bursa, Turkey, 10 - 12 September 2025, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/asyu67174.2025.11208351
  • City: Bursa
  • Country: Turkey
  • Keywords: computer vision, DenseNet121, LSTM, smart video surveillance, video processing, violence
  • Bilecik Şeyh Edebali University Affiliated: Yes

Abstract

This study proposes and tests a classification approach that performs spatial feature extraction with a pretrained deep convolutional neural network (CNN) model, DenseNet-121, and temporal pattern analysis with a long-shortterm memory (LSTM) model to classify short-length video clips into 'violent' and 'non-violent' categories. The proposed hybrid method is trained using the Real Life Violent Situations (RLVS) dataset and tested with a 5-fold cross-validation method. The results show that the proposal achieves an average accuracy of 95.22% and provides a generalizable performance with a standard deviation value of 0.64%.