2019-092 – Segmentation of Fire and Smoke from Infra-Red Videos using Multiple Unsupervised Algorithms

Background Fire and smoke detectors are not only an important part of the firefighting system but are also imperative in monitoring indoor buildings and outside environments. Conventional detection systems use built-in sensors which set off the alarm only when the particles reach the sensors. This configuration makes these detectors highly inefficient due to delay in response times. New technology such as vision-based fire and smoke detecting systems were introduced as appropriate alternatives to the conventional methods over the past few years. However, these systems primarily use either the color information of fire and smoke or the dynamic motion features, which can often result in high false alarm rates. There exists a present market need for new, advanced technologies that allow for more accurate categorization and enhanced capability for detecting fire and smoke. Technology Description Researchers at the University of New Mexico have developed a novel approach for the accurate detection of fire and smoke. This proposed technology utilizes a vision-based fire and smoke segmentation system which uses spatial, temporal and motion information to extract the desired regions from the video frames. The fusion of information is done using multiple features such as optical flow, divergence and intensity values. The features extracted from the images are used to segment the pixels into different classes in an unsupervised way following which, a comparative analysis is performed by using multiple clustering algorithms for segmentation. This enhanced information improves real-time firefighting decision-making and minimizes errors in judgment induced by environmental conditions and anxiety levels. Andrew Roerick aroerick@innovations.unm.edu 505-277-0608

Related Blog

Smart, interactive desk

Get ready to take your space management game to the next level with the University of Glasgow’s innovative project! By combining the

Mechanical Hamstring™

University of Delaware Technology Overview This device was created to allow athletes who suffer a hamstring strain to return to the field

Join Our Newsletter

                                                   Receive Innovation Updates, New Listing Highlights And More