Analysis of real-time hostile activitiy detection from spatiotemporal features using time distributed deep convolutional neural networks, recurrent neural networks and attention-based mechanisms
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.
| Główni autorzy: | , , , |
|---|---|
| Kolejni autorzy: | |
| Format: | Praca dyplomowa |
| Język: | en_US |
| Wydane: |
Brac University
2022
|
| Hasła przedmiotowe: | |
| Dostęp online: | http://hdl.handle.net/10361/17652 |
| id |
10361-17652 |
|---|---|
| record_format |
dspace |
| spelling |
10361-176522023-10-11T10:31:14Z Analysis of real-time hostile activitiy detection from spatiotemporal features using time distributed deep convolutional neural networks, recurrent neural networks and attention-based mechanisms Siddique, Labib Ahmed Junhai, Rabita Islam, Moshfeka Qader, Shafinaz Chakrabarty, Dr. Amitabha Reza, Tanzim Rahman, Tanvir Department of Computer Science and Engineering, Brac University Artificial Intelligence Deep learning Neural network Violence detection Video classification Attention based encoder LRCN ConvLSTM Transformer C3D Neural networks (Computer science) Neural network. Deep learning (Machine learning) This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022. Cataloged from PDF version of thesis. Includes bibliographical references (pages 48-51). Throughout time, there has been a surge of hostile activities in public places across the globe. With the advancement in technology, it has been possible to monitor public places through real time surveillance. Video surveillance has become essential for ensuring public safety as it provides a significant benefit in lowering the crime rate, as well as monitoring the facility within its reach. Hence, CCTV cameras are installed in all areas where security is a priority. Although CCTV cameras help a lot in increasing security, the main drawback in these surveillance systems is that it requires constant human interaction and monitoring. To eradicate this issue, an automated surveillance system can be built using artificial intelligence, deep learning and IoT (Internet of things). So in this research we explore deep learn ing video classification techniques that can help us automate surveillance systems to detect violence as they are happening. Traditional machine learning or image classification techniques fall short when it comes to classifying videos as they attempt to classify each frame separately for which the predictions start to flicker. So many researchers are coming up with video classification techniques that consider spatiotemporal features while classifying. However, deploying these deep learning models are not always practical in an IoT environment. For this reason we cannot use techniques that are acquired like skeleton points and optical flow through technologies like pose estimation or depth sensors. Although these techniques ensure a higher accuracy score, they are computationally heavy. Keeping these constraints in mind, we experimented with various video classification and action recognition techniques such as ConvLSTM, LRCN (with both custom CNN layers and VGG-16 as feature extractor) CNN-Transformer and C3D (3D-CNN). We achieved a test accuracy of 80% on ConvLSTM, 83.33% on CNN-BiLSTM, 70% on VGG16-BiLstm ,76.76% on CNN-Transformer and 80% on C3D model. Labib Ahmed Siddique Rabita Junhai Moshfeka Islam Shafinaz Qader B. Computer Science and Engineering 2022-12-14T09:22:07Z 2022-12-14T09:22:07Z 2022 2022-05 Thesis ID: 18101478 ID: 18101259 ID: 18101432 ID: 18141006 http://hdl.handle.net/10361/17652 en_US 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. 51 Pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
en_US |
| topic |
Artificial Intelligence Deep learning Neural network Violence detection Video classification Attention based encoder LRCN ConvLSTM Transformer C3D Neural networks (Computer science) Neural network. Deep learning (Machine learning) |
| spellingShingle |
Artificial Intelligence Deep learning Neural network Violence detection Video classification Attention based encoder LRCN ConvLSTM Transformer C3D Neural networks (Computer science) Neural network. Deep learning (Machine learning) Siddique, Labib Ahmed Junhai, Rabita Islam, Moshfeka Qader, Shafinaz Analysis of real-time hostile activitiy detection from spatiotemporal features using time distributed deep convolutional neural networks, recurrent neural networks and attention-based mechanisms |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022. |
| author2 |
Chakrabarty, Dr. Amitabha |
| author_facet |
Chakrabarty, Dr. Amitabha Siddique, Labib Ahmed Junhai, Rabita Islam, Moshfeka Qader, Shafinaz |
| format |
Thesis |
| author |
Siddique, Labib Ahmed Junhai, Rabita Islam, Moshfeka Qader, Shafinaz |
| author_sort |
Siddique, Labib Ahmed |
| title |
Analysis of real-time hostile activitiy detection from spatiotemporal features using time distributed deep convolutional neural networks, recurrent neural networks and attention-based mechanisms |
| title_short |
Analysis of real-time hostile activitiy detection from spatiotemporal features using time distributed deep convolutional neural networks, recurrent neural networks and attention-based mechanisms |
| title_full |
Analysis of real-time hostile activitiy detection from spatiotemporal features using time distributed deep convolutional neural networks, recurrent neural networks and attention-based mechanisms |
| title_fullStr |
Analysis of real-time hostile activitiy detection from spatiotemporal features using time distributed deep convolutional neural networks, recurrent neural networks and attention-based mechanisms |
| title_full_unstemmed |
Analysis of real-time hostile activitiy detection from spatiotemporal features using time distributed deep convolutional neural networks, recurrent neural networks and attention-based mechanisms |
| title_sort |
analysis of real-time hostile activitiy detection from spatiotemporal features using time distributed deep convolutional neural networks, recurrent neural networks and attention-based mechanisms |
| publisher |
Brac University |
| publishDate |
2022 |
| url |
http://hdl.handle.net/10361/17652 |
| work_keys_str_mv |
AT siddiquelabibahmed analysisofrealtimehostileactivitiydetectionfromspatiotemporalfeaturesusingtimedistributeddeepconvolutionalneuralnetworksrecurrentneuralnetworksandattentionbasedmechanisms AT junhairabita analysisofrealtimehostileactivitiydetectionfromspatiotemporalfeaturesusingtimedistributeddeepconvolutionalneuralnetworksrecurrentneuralnetworksandattentionbasedmechanisms AT islammoshfeka analysisofrealtimehostileactivitiydetectionfromspatiotemporalfeaturesusingtimedistributeddeepconvolutionalneuralnetworksrecurrentneuralnetworksandattentionbasedmechanisms AT qadershafinaz analysisofrealtimehostileactivitiydetectionfromspatiotemporalfeaturesusingtimedistributeddeepconvolutionalneuralnetworksrecurrentneuralnetworksandattentionbasedmechanisms |
| _version_ |
1814307877761843200 |