Video-based fire detection | |
| Author | Perera, Thammitage J.D. Rushanka |
| Call Number | AIT Caps. Proj. no.EL-15-13 |
| Subject(s) | Fire detectors Safety measures Video Based Technologies |
| Note | A capstone project submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Engineering in Electronics Engineering, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Caps. Proj. ; no. EL-15-13 |
| Abstract | Now-days video-based fire detection has become an essential part in safety. Since tradition fire detection systems are not effective and they are limited by slow response time and also give false fire detection. Because that sensor based video fire detection begun with the technology revolution. In this paper I have consider three fire detection methods using two types of cameras. They are Microsoft Kinect and Sentry360 IR camera. Kinect provides RGB image and Depth image at same time. Fire can be identified distinguish from background in depth image as well as IR image. That feature has used to separate fire pixels from the background. To compare the three methods I have used existing algorithm to the RGB output and two different algorithms were developed to the depth image and IR image. When comparing three methods U considered manually detected number of fire frames along with the number of detected fire frames by the algorithm. These two developed algorithms were tested using fire and a moving red color object. |
| Year | 2015 |
| Corresponding Series Added Entry | Asian Institute of Technology. Caps. Proj. ; no. EL-15-13 |
| Type | Project |
| School | School of Engineering and Technology (SET) |
| Department | Bachelor Degree |
| Academic Program/FoS | Electronic Engineering (EL) |
| Chairperson(s) | Mongkol Ekpanyapong; |
| Examination Committee(s) | Dailey, Matthew ; |
| Degree | Capstone Project (B.Sc.)-Asian Institute of Technology, 2015 |