Surrya Viknesh A/l Chandra Segar (2022) Aggressive behaviour detection system for lift using convolutional neural network. Universiti Malaysia Sabah. (Unpublished)
![[img]](https://eprints.ums.edu.my/style/images/fileicons/text.png) |
Text
AGGRESSIVE BEHAVIOUR DETECTION SYSTEM FOR LIFT USING CONVOLUTIONAL NEURAL NETWORK.24pages.pdf Download (595kB) |
|
Text
AGGRESSIVE BEHAVIOUR DETECTION SYSTEM FOR LIFT USING CONVOLUTIONAL NEURAL NETWORK.pdf Restricted to Registered users only Download (2MB) |
Abstract
We live in a community that depends heavily on the use of CCTV cameras to maintain a high degree of surveillance. However, such a strategy is extremely problematic, as we typically use CCTV video just hours or even days after the incident has occurred (Febin,2019). It offers useful information in court but is seldom used to deter or respond to crime in real time. The explanation for this inefficiency is that the task of tracking vast amounts of CCTV footage is primarily carried out by a small number of security personnel. Fustigation, worker exhaustion, and discontinuity of observation make human monitoring ineffective. Action Recognition is an active research area in the field of computer vision, and it has broad implications in today's world, and the detection of aggressive action is of high importance as it is directly connected to our protection and welfare. The idea of an intelligent monitoring system is to automatically identify unusual activity in surveillance videos and therefore to enable security staff to take necessary action at the right time. Aggressive behaviour action recognition has significant importance in developing automated video surveillance systems (Akti,2019). In closed spaces such as a lift, aggressive behaviour poses a significant danger to physical security and social safety. It is therefore of considerable importance to automatically identify aggression activities from CCTV videos on the spot. The objectives of this project are ;(1) To design a deep learning based for aggressive behaviours in a lift, (2) To implement and optimize the structure of the deep learning architecture for aggressive behaviour detection and (3) To assess the performance of the proposed deep learning based aggressive behaviour detection. The proposed system has the potential to aid authorities and University management in security.
| Item Type: | Academic Exercise |
|---|---|
| Keyword: | Behaviour , Detection system , CCTV |
| Subjects: | Q Science > QA Mathematics > QA1-939 Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science > QA76.75-76.765 Computer software |
| Department: | FACULTY > Faculty of Computing and Informatics |
| Depositing User: | DG MASNIAH AHMAD - |
| Date Deposited: | 18 Jul 2022 19:17 |
| Last Modified: | 18 Jul 2022 19:17 |
| URI: | https://eprints.ums.edu.my/id/eprint/33291 |
Actions (login required)
 |
View Item |