• Pooja Guchait
• Chaitali Nimse
• Chetna Pradhan
• Pavlin Fernandes
• Shubhangi Kharche

Violence detection using human action recognition is a research area that aims to automatically recognize patterns of human actions that are indicative of violent behaviour. The goal of this approach is to develop computer vision and machine learning techniques that can analyse video footage and identify instances of violent behaviour in real-time. A violence detection project using human action recognition is needed to address the increasing need for improved safety and security in various settings. In contrast, the proposed system for violence detection using human action recognition involves using deep learning models, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), to automatically extract features from video frames and identify patterns of human movement associated with violent behaviour. The goal of the violence detection project is to develop a machine learning model that can automatically detect instances of violence in video footage. The input data for the model consists of video footage captured by surveillance cameras or other sources, and the output will be a binary classification indicating whether the footage contains violence or not. The model is trained on a large and diverse dataset of video footage that contains examples of both violent and non-violent behaviour. The success of the model is measured using standard evaluation metrics such as accuracy, precision, recall, and F1 score. The frames individually are given to the model to predict if the frames contain any action of violence or not. The model has a high accuracy in detecting violence while minimizing false positives and false negatives. The model is trained using the BidirectionalLSTM and an accuracy score of 0.92 (92%) is obtained.

"Violence Detection Using Human Action Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 7, page no.a548-a553, July-2023, Available :http://www.jetir.org/papers/JETIR2307068.pdf

"Violence Detection Using Human Action Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 7, page no. ppa548-a553, July-2023, Available at : http://www.jetir.org/papers/JETIR2307068.pdf