In this project, an investigation was performed to find ways of differencing between fires and vehicles at waste stations in hope of removing vehicles as a source of error during early fire detection. The existing system makes use of a heat camera, which rotates in 48 different angles (also known as zones) in a fixed position. If the heat is above a certain value within a zone the system sounds the fire alarm.The rotation of the camera results in an unwanted displacement between two successive frames within the same zone.
By use of image registration, this displacement waste moved. After the registration of an image, segmentation was performed where cold objects are eliminated as an error source. Lastly, an analysis was performed upon the warm objects.At the end, it was proven that the image registration had been a successful improvement of the existing system. It was also shown that vehicles can, to some extent, be eliminated as an error source.
Source: Linköping University
Author: Söderström, Rikard
>> 100+ Projects on Image Processing