author={Jos{\'e} Ramiro Mart{\'i}nez de Dios and Luis Merino and An{\'i}bal Ollero},
  journal={IFAC Proceedings Volumes},
Abstract The paper presents a system for automatic fire detection based on the use of autonomous aerial vehicles. Particularly, the application of a helicopter with infrared and visual cameras is described. The paper presents the techniques used for fire segmentation in visual and infrared cameras, and the procedures to fuse the data obtained from both of them. Furthermore the paper presents the techniques for automatic geolocation of the detected fire alarms. Experimental results are shown. 

Figures and Tables from this paper

Fire detection using infrared images for UAV-based forest fire surveillance

The presented algorithm makes use of brightness and motion clues along with image processing techniques based on histogram-based segmentation and optical flow approach for fire pixels detection for automatic detection of forest fires in infrared (IR) images.

Computer vision system for fire detection and report using UAVs

This article presents a review of the main uses of UAVs in combatting fire, with special emphasis on fire detection techniques using computer and infrared computer techniques, as well as the hardware systems that drones must incorporate to perform this task.

An Unmanned Aircraft System for Automatic Forest Fire Monitoring and Measurement

The paper shows how an UAS can automatically obtain information in real-time of the evolution of the fire front shape and potentially other parameters related to the fire propagation by means of on-board infrared or visual cameras.

An Unmanned Aircraft System for Automatic Forest Fire Monitoring and Measurement

The paper presents an Unmanned Aircraft System (UAS), consisting of several aerial vehicles and a central station, for forest fire monitoring. Fire monitoring is defined as the computation in

Multimodal three-dimensional vision for wildland fires detection and analysis

The obtained results show the efficiency of the proposed system for wildland fires research and firefighting decision support in operational scenarios.

Automatic Fire Detection Using Computer Vision Techniques for UAV-based Forest Fire Surveillance

  • C. Yuan
  • Environmental Science, Computer Science
  • 2017
A reliable and accurate forest fire detection algorithms which are applicable to UAVs are developed for distinguishing smoke from other analogues and achieving early stage fire detection.

Automatic Forest Fire Monitoring and Measurement using Unmanned Aerial Vehicles

It is shown how multiple UAVs can collaborate in fire monitoring activities, allowing to cover bigger fires or to obtain complementary views of a fire.

Fire Geometrical Characteristics Estimation Using a Visible Stereovision System Carried by Unmanned Aerial Vehicle

A framework composed by an unmanned aerial vehicle carrying a visible stereovision system developed in order to estimate the position, rate of spread, height, inclination angle, base width and surface of fires obtained by experimental burnings at field scale is presented.

A survey on technologies for automatic forest fire monitoring, detection, and fighting using unmanned aerial vehicles and remote sensing techniques

Technologies related to UAV forest fire monitoring, detection, and fighting are briefly reviewed, including those associated with fire detection, diagnosis, and prognosis, image vibration elimination, and cooperative control of UAVs.

Unsupervised Segmentation of Fire and Smoke From Infra-Red Videos

This paper proposes a vision-based fire and smoke segmentation system which uses spatial, temporal and motion information to extract the desired regions from the video frames and achieves a frame-wise fire detection rate of 95.39%.



Autonomous Forest Fire Detection

Forest fire detection is a very important issue in the pre-suppression process. Timely detection allows the suppression units to reach the fire in its initial stages and this will reduce the

An Intelligent System for False Alarm Reduction in Infrared Forest-Fire Detection

The False Alarm Reduction system is proposed, an alternative real-time infrared-visual system that overcomes the main issue for forest-fire detection systems, and provides the human operator with new software tools to verify alarms.

A new training-based approach for robust thresholding

The algorithm proposed is based on a learning process that extracts heuristic knowledge from training images and incorporates it in in fuzzy systems to be applied in the supervision of a fuzzy-multiresolution threshold selection method.

Feature-Level and Decision-Level Fusion of Noncoincidently Sampled Sensors for Land Mine Detection

It is found that fusion of binary decisions does not perform significantly better than the best available sensor, as is decision-level fusion when detection confidence information is also available ("soft-decision" fusion).

Alignment of non-overlapping sequences

  • Y. CaspiM. Irani
  • Computer Science
    Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001
  • 2001
Applications of this approach to alignment can be used not only for aligning nan-overlapping sequences, but also for handling other cases that are inherently difficult for standard image alignment techniques.

The Geometry of Multiple Images

Nitrocyclopropane is prepared by reacting 3-chloro-1-nitropropane with an amine which has a polar center in addition to an amino function in the presence of a polar, aprotic solvent. For example, the

Picture thresholding using an iterative selection method.

ANFIS: adaptive-network-based fuzzy inference system

  • J. Jang
  • Computer Science
    IEEE Trans. Syst. Man Cybern.
  • 1993
The architecture and learning procedure underlying ANFIS (adaptive-network-based fuzzy inference system) is presented, which is a fuzzy inference system implemented in the framework of adaptive

FUEGO : A low cost service for fire detection

    FUEGO: A low cost service for fire detection

    • Proc. 3 rd Int'l. Conf. on Forest Fire Research
    • 1998