Development of a neuro-fuzzy based intrusion monitoring and data logging security system for agricultural farmlands
Crime is one of the major problems here in the Philippines. Crimes can happen in public or private places such as in buildings, colleges, business or private properties. With the aid of surveillance systems, it did help a lot in terms of the security and protection of the citizens as well as the est...
Saved in:
| Main Author: | |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Animo Repository
2019
|
| Subjects: | |
| Online Access: | https://animorepository.dlsu.edu.ph/etd_doctoral/1499 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | De La Salle University |
| Language: | English |
| Summary: | Crime is one of the major problems here in the Philippines. Crimes can happen in public or private places such as in buildings, colleges, business or private properties. With the aid of surveillance systems, it did help a lot in terms of the security and protection of the citizens as well as the establishments that have been installed with surveillance systems.
A Closed Circuit Television (CCTV) Surveillance system is primarily used for monitoring a particular vicinity 24/7. One of the subsystems of a surveillance system is the Digital Video Recorder which records the real-time footage taken by CCTV Cameras. Some of the existing Digital Video Recorder (DVR) has limited functions in recording, it only features motion detection. In current CCTV systems, target identification is always limited to human intervention, and in addition, data logging is not yet integrated into DVRs which are only limited to recording. A video surveillance system is very beneficial especially to crimes such as theft or burglary.
This Dissertation paper is an implementation of Fuzzy Logic and Convolutional Neural Network on surveillance systems that identifies targets under real-time. The Algorithm works under multiple iterations until it reached the target specified facial features upon trained datasets. The system accuracy lies on the Confidence score on each face vector detected. A developed virtual video recording algorithm will be used to integrate a DVR hardware to the face identifier and classifier system.
The developed Algorithm acts as a Virtual Instrument Video Adapter for Digital Data Multiplexing with Facial Vector Identification. |
|---|