Anglia Ruskin University
Sadeghi-Esfahlani_et_al_2018_2.pdf (2.09 MB)

Fire detection of Unmanned Aerial Vehicle in a Mixed Reality-based System

Download (2.09 MB)
conference contribution
posted on 2023-08-30, 15:13 authored by Shabnam Sadeghi Esfahlani, Silvia Cirstea, Alireza Sanaei, Marcian N. Cirstea
This paper proposes the employment of a low-cost Micro-electro-mechanical system including; inertial measurement unit (IMU), a consumer-grade digital camera and a fire detection algorithm with a nano unmanned aerial vehicle for inspection application. The video stream (monocular camera) and navigation data (IMU) rely on state-of-the-art indoor/outdoor navigation system. The system combines robotic operating system and computer vision techniques to render metric scale of monocular vision and gravity observable to provide robust, accurate and novel inter-frame motion estimates. The collected onboard data are communicated to the ground station and processed using a Simultaneous Localisation and Mapping (SLAM) system. A robust and efficient re-localisation SLAM was performed to recover from tracking failure, motion blur and frame lost in the received data. The fire detection algorithm was deployed based on the colour, movement attributes, temporal variation of fire's intensity and its accumulation around a point. A cumulative time derivative matrix was used to detect areas with fire's high-frequency luminance flicker (random characteristic) to analyse the frame-by-frame changes. We considered colour, surface coarseness, boundary roughness and skewness features while the quadrotor flies autonomously within clutter and congested areas. Mixed Reality system was adopted to visualise and test the proposed system in a physical/virtual environment. The results showed that the UAV could successfully detect fire and flame, fly towards and hover around it, communicate with the ground station and generate SLAM system.


Page range






Place of publication




Conference proceeding

IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society

Name of event

IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society


Washington DC, USA

Event start date


Event finish date


File version

  • Accepted version


  • eng

Legacy posted date


Legacy creation date


Legacy Faculty/School/Department

Faculty of Science & Engineering


© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Usage metrics

    ARU Outputs


    No categories selected