Video surveillance using raspberry PI GPU
Today, surveillance system is being utilized and deployed in many places to provide supervision and bring security to people. The most commonly used technology currently is Closed-Circuit Television (CCTV). However, there are several defects with the technology such as anomalies cannot be identified...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/79581/1/WongYanYinPFKE2018.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my-utm-ep.79581 |
|---|---|
| record_format |
uketd_dc |
| spelling |
my-utm-ep.795812018-10-31T13:00:14Z Video surveillance using raspberry PI GPU 2018 Wong, Yan Yin TK Electrical engineering. Electronics Nuclear engineering Today, surveillance system is being utilized and deployed in many places to provide supervision and bring security to people. The most commonly used technology currently is Closed-Circuit Television (CCTV). However, there are several defects with the technology such as anomalies cannot be identified automatically and expensive. This project proposed to use the GPU in Raspberry Pi for video surveillance task. Raspberry Pi is a powerful single-board computer which features an ARM processor and a VideoCore IV graphics processing unit (GPU). It is sufficiently powerful to work as a video surveillance system and relatively cheap compared to CCTV. Furthermore, GPU is optimized for parallel computing of video data. It can theoretically provides better performance and have higher efficiency in video processing compared to CPU. Hence, the GPU in Raspberry Pi should provides large performance gain by porting the algorithm from CPU-only reference to works on GPU. The objective of this project is to explore on how the GPU can be programmed for the purpose of video surveillance. 2018 Thesis http://eprints.utm.my/id/eprint/79581/ http://eprints.utm.my/id/eprint/79581/1/WongYanYinPFKE2018.pdf application/pdf en public masters Universiti Teknologi Malaysia, Faculty of Electrical Engineering Faculty of Electrical Engineering |
| institution |
Universiti Teknologi Malaysia |
| collection |
UTM Institutional Repository |
| language |
English |
| topic |
TK Electrical engineering Electronics Nuclear engineering |
| spellingShingle |
TK Electrical engineering Electronics Nuclear engineering Wong, Yan Yin Video surveillance using raspberry PI GPU |
| description |
Today, surveillance system is being utilized and deployed in many places to provide supervision and bring security to people. The most commonly used technology currently is Closed-Circuit Television (CCTV). However, there are several defects with the technology such as anomalies cannot be identified automatically and expensive. This project proposed to use the GPU in Raspberry Pi for video surveillance task. Raspberry Pi is a powerful single-board computer which features an ARM processor and a VideoCore IV graphics processing unit (GPU). It is sufficiently powerful to work as a video surveillance system and relatively cheap compared to CCTV. Furthermore, GPU is optimized for parallel computing of video data. It can theoretically provides better performance and have higher efficiency in video processing compared to CPU. Hence, the GPU in Raspberry Pi should provides large performance gain by porting the algorithm from CPU-only reference to works on GPU. The objective of this project is to explore on how the GPU can be programmed for the purpose of video surveillance. |
| format |
Thesis |
| qualification_level |
Master's degree |
| author |
Wong, Yan Yin |
| author_facet |
Wong, Yan Yin |
| author_sort |
Wong, Yan Yin |
| title |
Video surveillance using raspberry PI GPU |
| title_short |
Video surveillance using raspberry PI GPU |
| title_full |
Video surveillance using raspberry PI GPU |
| title_fullStr |
Video surveillance using raspberry PI GPU |
| title_full_unstemmed |
Video surveillance using raspberry PI GPU |
| title_sort |
video surveillance using raspberry pi gpu |
| granting_institution |
Universiti Teknologi Malaysia, Faculty of Electrical Engineering |
| granting_department |
Faculty of Electrical Engineering |
| publishDate |
2018 |
| url |
http://eprints.utm.my/id/eprint/79581/1/WongYanYinPFKE2018.pdf |
| _version_ |
1747818261383217152 |