Using deep learning algorithms to detect violent activities

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2019.

Detalhes bibliográficos
Main Authors: Ammar, S.M. Rojin, Anjum, Md. Tanvir Rounak, Islam, Md. Touhidul Islam
Outros Autores: Alam, Md. Ashraful
Formato: Thesis
Idioma:English
Publicado em: BRAC University 2019
Assuntos:
Acesso em linha:http://hdl.handle.net/10361/12270
id 10361-12270
record_format dspace
spelling 10361-122702022-01-26T10:20:09Z Using deep learning algorithms to detect violent activities Ammar, S.M. Rojin Anjum, Md. Tanvir Rounak Islam, Md. Touhidul Islam Alam, Md. Ashraful Department of Computer Science and Engineering, Brac University Machine learning Violence detection Neural network DarkNet-19 Machine learning. This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2019. Cataloged from PDF version of thesis. Includes bibliographical references (pages 35-40). It is of extensive importance to develop a technique for automatic surveillance video analysis to recognize the presence of violence. In this work, to identify violent videos, we put forward a deep neural network. For extracting frame level features from a video, a convolutional neural network is used with a pre-trained ImageNet model. The characteristics of the frame level are then aggregated using a long short-term memory variant that uses fully connected layers and leaky recti ed linear units. Together with the long short-term memory, the convolutional neural network is capable of capturing localized spatio-temporal features that enable the analysis of local motion in the video. The performance is further evaluated in terms of accuracy of recognition on three standard benchmark datasets. In order to determine the capabilities of our proposed model, we also compared our system results with other techniques. The approach proposed outperforms state-of - the-art methods while processing the videos in real time. S.M. Rojin Ammar Md. Tanvir Rounak Anjum Md. Touhidul Islam B. Computer Science and Engineering 2019-06-30T03:46:35Z 2019-06-30T03:46:35Z 2019 2019-05 Thesis ID 15101026 ID 16301140 ID 15301133 http://hdl.handle.net/10361/12270 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 40 pages application/pdf BRAC University
institution Brac University
collection Institutional Repository
language English
topic Machine learning
Violence detection
Neural network
DarkNet-19
Machine learning.
spellingShingle Machine learning
Violence detection
Neural network
DarkNet-19
Machine learning.
Ammar, S.M. Rojin
Anjum, Md. Tanvir Rounak
Islam, Md. Touhidul Islam
Using deep learning algorithms to detect violent activities
description This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2019.
author2 Alam, Md. Ashraful
author_facet Alam, Md. Ashraful
Ammar, S.M. Rojin
Anjum, Md. Tanvir Rounak
Islam, Md. Touhidul Islam
format Thesis
author Ammar, S.M. Rojin
Anjum, Md. Tanvir Rounak
Islam, Md. Touhidul Islam
author_sort Ammar, S.M. Rojin
title Using deep learning algorithms to detect violent activities
title_short Using deep learning algorithms to detect violent activities
title_full Using deep learning algorithms to detect violent activities
title_fullStr Using deep learning algorithms to detect violent activities
title_full_unstemmed Using deep learning algorithms to detect violent activities
title_sort using deep learning algorithms to detect violent activities
publisher BRAC University
publishDate 2019
url http://hdl.handle.net/10361/12270
work_keys_str_mv AT ammarsmrojin usingdeeplearningalgorithmstodetectviolentactivities
AT anjummdtanvirrounak usingdeeplearningalgorithmstodetectviolentactivities
AT islammdtouhidulislam usingdeeplearningalgorithmstodetectviolentactivities
_version_ 1814309278764236800