For the detection of small targets, fire-like and smoke-like targets in forest fire images, as well under different natural lights, an improved Fire-YOLO deep learning algorithm is proposed. The model expands feature extraction network from three dimensions, which enhances propagation identification, improves performance, reduces parameters. Furthermore, through promotion pyramid, top-performin...

Finding smoke in surveillance videos can be crucial in early detection of fire emergencies. Such early detections improve damage prevention and control by enabling the authorities to take the necessary precautionary steps. This paper describes a smoke detection technique developed for videos taken in visual band. The method makes use of optical flow and color filtering to detect smoke covered r...

EXECUTIVE SUMMARY To investigate the performance of the current emergency ventilation strategies of both the L.-H.-La Fontaine and the Ville-Marie tunnels in the event of a fire, a research project is being conducted by the Fire Risk Management Program of the Institute of Research in Construction of the National Research Council of Canada (B-4258). The research project will use Computational Fl...

Smoke from fires significantly influences climate, weather, and human health. Fire smoke is traditionally detected using an aerosol index calculated spectral contrast changes. However, such methods usually miss thin plumes. It also remains challenging to accurately separate plumes dust, clouds, bright surfaces. To improve plume detections, this paper presents a new scattering-based detection al...

Air conditioning control systems are commonly installed in restaurants, commercial buildings, office buildings and institutional buildings in Hong Kong. The systems invariably involve the use of fans for moving the air, filters for cleansing, ducts for air distribution, a control system for regulating the amount of heating or cooling automatically and a refrigerating plant connected to the heat...

moderate resolution imaging spectroradiometer (modis) have been widely used for active fire detection in the world as the specific channels used for the fire detection have made the modis images applicable. the main objective was to explore the capability of modis images for active fire detection in the zagross forests using the modis contextual algorithm. the study was performed in the marivan...

This study sought an effective detection method not only for flame but also the smoke generated in event of a fire. To this end, region was pre-processed using color conversion and corner method, could be detected dark channel prior optical flow. eliminates unnecessary background regions allows selection fire-related regions. Where there interest, inference conducted deep-learning-based convolu...

Laboratory experiments were conducted to determine the responses of a prototype smoke detector and a commercially available photoelectric smoke detector to smoke particles generated from various combustion sources. The prototype smoke detector combines optical scattering measurements with ionization chamber measurements in order to reduce/eliminate nuisance alarms due to the presence of airborn...