A non-temporal texture driven approach to real-time fire detection

Abstract

Here we investigate the automatic detection of fire pixel regions in conventional video (or still) imagery within realtime bounds. As an extension to prior, established approaches within this field we specifically look to extend the primary use of threshold-driven colour spectroscopy to the combined use of colour-texture feature descriptors as an input to a trained classification approach that is independent of temporal information. We show the limitations of such spectroscopy driven approaches on simple, real-world examples and propose our novel extension as a robust, real-time solution within this field by combining simple texture descriptors to illustrate maximal 98% fire region detection.

Fire Detection in Video Sequences Based on Static and Dynamic Features

“…In contrast to work on fire detection [12], texture features are calculated for a gray-scale CFR after applying a local binary pattern operator. Ojala et al [18] introduced the LBP (local binary pattern) operator in 1996 as a means of summarizing local gray-level structure.…”

“…The algorithm does not use a background subtraction method and therefore it can be used with moving cameras, but he works well when the fire is clearly visible and in close range so that the flicker and irregular nature of flames are observable. Chenebert et al [12] use a combined texture and color based feature descriptor as an input to a trained classifier based detection boundary. Feature classification is performed based on isolation of candidate fire pixel regions using a basic color spectroscopy approach and combined color-texture classification of these regions using a trained classification approach.…”

Robust motion filtering as an enabler to video stabilization for a tele-operated mobile robot

“…Illustrative frame extracts from building approach sequence (1) Figure 20. Illustrative frame extracts from building approach sequence (2) of the vehicle at two different speeds. These speeds (measured in pixels/s.…”

“…The use of tele-operated robotic ground vehicles is now commonplace in many hazardous environments across defence, security, rescue and industrial domains [1,2]. The capability to navigate remotely via wireless communication over a large variety of terrain, under varying environmental conditions, makes them second to none in a wide range of taskings.…”

“…2-frame, 80ms at 25fps). This has a wide range of applications in autonomous robotics [5][6][7], automotive visual sensing [8][9][10][11][12][13][14] and general autonomous sensing applications [2,[15][16][17].…”