Please use this identifier to cite or link to this item: https://rda.sliit.lk/handle/123456789/1125
Title: Intelligent Violence Video Detection System
Authors: Jayasanka, H.K.B.
Jayasanka, B.M.R.D.
Diyunuge, K.D.C.D.R.
Jayasekara, T.H.D.Y.M.
Lunugalage, D.
Samaratunge, U.S.S.
Keywords: Deep learning
Image processing
Violence detection
Artificial Intelligent
Issue Date: 9-Dec-2021
Publisher: 2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT
Abstract: Due to the busy and stressful lifestyle, humans tend to feel frustrated frequently. This harmful emotional behavior results in violations of several rules, regulations and legislation. Violence is one of the serious issues which emerges due to this situation. It also results in uncontrollable human behavior. This behavior can either be verbal arguments or even physical conflicts. A trend of recording and publishing videos related to these kinds of violations in various platforms can be observed widely at present. Therefore, the terms and conditions of these platforms are subjected to frequent changes. Difficulty in identifying and controlling of violent events will result in an increase of such cases. Due to these reasons, the demand for violence detection systems will be significantly increased. Efficient violent detection systems are lacking currently. But, the usage of artificial intelligence in these systems are further limited. Four major components have been used to achieve this goal. They are video-based, embedded audio-based, abused textbased and thumbnail-based violence detection. The machine learning and image processing techniques are used along with these components to improve the clarity of violence detection.
URI: http://rda.sliit.lk/handle/123456789/1125
ISSN: 978-1-6654-0862-2/21
Appears in Collections:3rd International Conference on Advancements in Computing (ICAC) | 2021
Department of Information Technology-Scopes

Files in This Item:
File Description SizeFormat 
Intelligent_Violence_Video_Detection_System.pdf
  Until 2050-12-31
1.41 MBAdobe PDFView/Open Request a copy


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.