Video surveillance: Front-yard monitoring
Home intrusion is a severe crime that disrupts the safety and well-being of neighbourhoods. It has been happening at a shocking rate in recent years. Families have tried curbing the issue by implementing CCTVs and motion sensors. However, these approaches have considerable flaws, including over-rely...
| Main Author: | |
|---|---|
| Format: | Final Year Project / Dissertation / Thesis |
| Published: |
2023
|
| Subjects: | |
| Online Access: | http://eprints.utar.edu.my/5773/ http://eprints.utar.edu.my/5773/1/fyp_CS_2023_LBKS.pdf |
| _version_ | 1848886500946608128 |
|---|---|
| author | Low, Bryan Keng Seong |
| author_facet | Low, Bryan Keng Seong |
| author_sort | Low, Bryan Keng Seong |
| building | UTAR Institutional Repository |
| collection | Online Access |
| description | Home intrusion is a severe crime that disrupts the safety and well-being of neighbourhoods. It has been happening at a shocking rate in recent years. Families have tried curbing the issue by implementing CCTVs and motion sensors. However, these approaches have considerable flaws, including over-relying on human supervision and high false positive alarms.
With the latest technological advancements, an approach with computer vision techniques is proposed to aid crime identification. This project aims to deliver an automated front-yard intrusion system. It addresses the significant issues of CCTVs and motion sensors by removing the need for manual video monitoring and reducing false positive cases.
The proposed intelligent surveillance system is expected to have two vital functionalities. The first feature is to give a mild warning if a person has stepped foot into the front yard or the restricted area. Here, the YOLO algorithm will be used for human detection.
When there is a human presence, the second stage checks for excessive motions resembling violence with dense optical flow. The model will be evaluated with several video datasets containing intrusions and violence. It will trigger an alarm when violent activities such as fighting or snatching theft happen.
The system’s primary purpose is to reduce victims’ potential loss and damage by providing immediate notifications on intrusion without delay. |
| first_indexed | 2025-11-15T19:39:29Z |
| format | Final Year Project / Dissertation / Thesis |
| id | utar-5773 |
| institution | Universiti Tunku Abdul Rahman |
| institution_category | Local University |
| last_indexed | 2025-11-15T19:39:29Z |
| publishDate | 2023 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | utar-57732023-09-08T13:50:13Z Video surveillance: Front-yard monitoring Low, Bryan Keng Seong Q Science (General) T Technology (General) Home intrusion is a severe crime that disrupts the safety and well-being of neighbourhoods. It has been happening at a shocking rate in recent years. Families have tried curbing the issue by implementing CCTVs and motion sensors. However, these approaches have considerable flaws, including over-relying on human supervision and high false positive alarms. With the latest technological advancements, an approach with computer vision techniques is proposed to aid crime identification. This project aims to deliver an automated front-yard intrusion system. It addresses the significant issues of CCTVs and motion sensors by removing the need for manual video monitoring and reducing false positive cases. The proposed intelligent surveillance system is expected to have two vital functionalities. The first feature is to give a mild warning if a person has stepped foot into the front yard or the restricted area. Here, the YOLO algorithm will be used for human detection. When there is a human presence, the second stage checks for excessive motions resembling violence with dense optical flow. The model will be evaluated with several video datasets containing intrusions and violence. It will trigger an alarm when violent activities such as fighting or snatching theft happen. The system’s primary purpose is to reduce victims’ potential loss and damage by providing immediate notifications on intrusion without delay. 2023-01 Final Year Project / Dissertation / Thesis NonPeerReviewed application/pdf http://eprints.utar.edu.my/5773/1/fyp_CS_2023_LBKS.pdf Low, Bryan Keng Seong (2023) Video surveillance: Front-yard monitoring. Final Year Project, UTAR. http://eprints.utar.edu.my/5773/ |
| spellingShingle | Q Science (General) T Technology (General) Low, Bryan Keng Seong Video surveillance: Front-yard monitoring |
| title | Video surveillance: Front-yard monitoring |
| title_full | Video surveillance: Front-yard monitoring |
| title_fullStr | Video surveillance: Front-yard monitoring |
| title_full_unstemmed | Video surveillance: Front-yard monitoring |
| title_short | Video surveillance: Front-yard monitoring |
| title_sort | video surveillance: front-yard monitoring |
| topic | Q Science (General) T Technology (General) |
| url | http://eprints.utar.edu.my/5773/ http://eprints.utar.edu.my/5773/1/fyp_CS_2023_LBKS.pdf |