Free Standard AU & NZ Shipping For All Book Orders Over $80!
Register      Login
International Journal of Wildland Fire International Journal of Wildland Fire Society
Journal of the International Association of Wildland Fire
RESEARCH ARTICLE

Automated location of active fire perimeters in aerial infrared imaging using unsupervised edge detectors

M. M. Valero A , O. Rios A , E. Pastor A B and E. Planas A
+ Author Affiliations
- Author Affiliations

A Department of Chemical Engineering, Centre for Technological Risk Studies, Universitat Politècnica de Catalunya – BarcelonaTech, Eduard Maristany 10-14, E-08019 Barcelona, Spain.

B Corresponding author. Email: elsa.pastor@upc.edu

International Journal of Wildland Fire 27(4) 241-256 https://doi.org/10.1071/WF17093
Submitted: 6 June 2017  Accepted: 19 February 2018   Published: 23 April 2018

Abstract

A variety of remote sensing techniques have been applied to forest fires. However, there is at present no system capable of monitoring an active fire precisely in a totally automated manner. Spaceborne sensors show too coarse spatio-temporal resolutions and all previous studies that extracted fire properties from infrared aerial imagery incorporated manual tasks within the image processing workflow. As a contribution to this topic, this paper presents an algorithm to automatically locate the fuel burning interface of an active wildfire in georeferenced aerial thermal infrared (TIR) imagery. An unsupervised edge detector, built upon the Canny method, was accompanied by the necessary modules for the extraction of line coordinates and the location of the total burned perimeter. The system was validated in different scenarios ranging from laboratory tests to large-scale experimental burns performed under extreme weather conditions. Output accuracy was computed through three common similarity indices and proved acceptable. Computing times were below 1 s per image on average. The produced information was used to measure the temporal evolution of the fire perimeter and automatically generate rate of spread (ROS) fields. Information products were easily exported to standard Geographic Information Systems (GIS), such as GoogleEarth and QGIS. Therefore, this work contributes towards the development of an affordable and totally automated system for operational wildfire surveillance.

Additional keywords: image analysis, monitoring, perimeter tracking, remote sensing, segmentation, wildland fire.


References

Ambrosia VG, Wegener SS (2009) Unmanned airborne platforms for disaster remote sensing support. In ‘Geoscience and Remote Sensing’. (Ed. P-GP Ho) pp. 91–114. (InTech)

Ambrosia VG, Wegener SS, Zajkowski T, Sullivan DV, Buechel S, Enomoto F, Lobitz B, Johan S, Brass J, Hinkley E (2011a) The Ikhana unmanned airborne system (UAS) western states fire imaging missions: from concept to reality (2006 – 2010). Geocarto International 26, 85–101.
The Ikhana unmanned airborne system (UAS) western states fire imaging missions: from concept to reality (2006 – 2010).Crossref | GoogleScholarGoogle Scholar |

Ambrosia VG, Sullivan DV, Buechel SW (2011b) Integrating sensor data and geospatial tools to enhance real-time disaster management capabilities: wildfire observations. Geological Society of America, Special Paper 482.

Baddeley A (1992) An error metric for binary images. In ‘Robust Computer Vision: Quality of Vision Algorithms’. (Eds W. Förstner and S. Ruwiedel) pp. 59–78 (Wichmann: Karlsruhe, Germany)

Borges PVK, Izquierdo E (2010) A probabilistic approach for vision-based fire detection in videos. IEEE Transactions on Circuits and Systems for Video Technology 20, 721–731.
A probabilistic approach for vision-based fire detection in videos.Crossref | GoogleScholarGoogle Scholar |

Boschetti L, Roy DP, Justice CO, Giglio L (2010) Global assessment of the temporal reporting accuracy and precision of the MODIS burned area product. International Journal of Wildland Fire 19, 705–709.
Global assessment of the temporal reporting accuracy and precision of the MODIS burned area product.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BC3cXhtFOkur%2FO&md5=1c163b714f60b0191014e6defe7911eeCAS |

Canny J (1986) A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-8, 679–698.
A computational approach to edge detection.Crossref | GoogleScholarGoogle Scholar |

Çelik T, Demirel H (2009) Fire detection in video sequences using a generic color model. Fire Safety Journal 44, 147–158.
Fire detection in video sequences using a generic color model.Crossref | GoogleScholarGoogle Scholar |

Çetin AE, Dimitropoulos K, Gouverneur B, Grammalidis N, Günay O, Habiboğlu YH, Töreyin BU, Verstockt S (2013) Video fire detection – review. Digital Signal Processing: A Review Journal 23, 1827–1843.
Video fire detection – review.Crossref | GoogleScholarGoogle Scholar |

Chabrier S, Laurent H, Rosenberger C, Emile B (2008) Comparative study of contour detection evaluation criteria based on dissimilarity measures. EURASIP Journal on Image and Video Processing 2008, 1–13.
Comparative study of contour detection evaluation criteria based on dissimilarity measures.Crossref | GoogleScholarGoogle Scholar |

Cruz MG, Alexander ME (2013) Uncertainty associated with model predictions of surface and crown fire rates of spread. Environmental Modelling & Software 47, 16–28.
Uncertainty associated with model predictions of surface and crown fire rates of spread.Crossref | GoogleScholarGoogle Scholar |

Cruz MG, Matthews S, Gould J, Ellis P (2010) Fire dynamics in mallee–heath: fuel, weather and fire behaviour prediction in south Australian semi-arid shrublands. Bushfire Cooperative Research Centre, Technical Report A1001. Available at http://www.bushfirecrc.com/sites/default/files/firedynamicsinmalleeheathreport.pdf [Verified 3 April 2018]

Csiszar IA, Morisette JT, Giglio L (2006) Validation of active fire detection from moderate-resolution satellite sensors: the MODIS example in northern eurasia. IEEE Transactions on Geoscience and Remote Sensing 44, 1757–1764.
Validation of active fire detection from moderate-resolution satellite sensors: the MODIS example in northern eurasia.Crossref | GoogleScholarGoogle Scholar |

Dickinson MB, Hudak AT, Zajkowski T, Loudermilk EL, Schroeder W, Ellison L, Kremens RL, Holley W, Martinez O, Paxton A, Bright BC, O’Brien JJ, Hornsby B, Ichoku C, Faulring J, Gerace A, Peterson D, Mauceri J (2016) Measuring radiant emissions from entire prescribed fires with ground, airborne and satellite sensors – RxCADRE 2012. International Journal of Wildland Fire 25, 48–61.
Measuring radiant emissions from entire prescribed fires with ground, airborne and satellite sensors – RxCADRE 2012.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BC28Xmslegtw%3D%3D&md5=d281b62aacd8dcf70e3b90b57784ef3dCAS |

Domènech R (2011) Efectivitat dels tractaments d’aclarida en la reducció del risc de propagació d’incendis en regenerats de pi blanc. PhD Thesis, Universitat Politècnica de Catalunya - BarcelonaTech. Available at http://hdl.handle.net/2117/94543 [Verified 3 April 2018]

Duane A, Piqué M, Castellnou M, Brotons L (2015) Predictive modelling of fire occurrences from different fire spread patterns in Mediterranean landscapes. International Journal of Wildland Fire 24, 407–418.
Predictive modelling of fire occurrences from different fire spread patterns in Mediterranean landscapes.Crossref | GoogleScholarGoogle Scholar |

Fernández-García NL, Medina-Carnicer R, Carmona-Poyato A, Madrid-Cuevas FJ, Prieto-Villegas M (2004) Characterization of empirical discrepancy evaluation measures. Pattern Recognition Letters 25, 35–47.
Characterization of empirical discrepancy evaluation measures.Crossref | GoogleScholarGoogle Scholar |

Finney MA, Cohen JD, McAllister SS, Jolly WM (2013) On the need for a theory of wildland fire spread. International Journal of Wildland Fire 22, 25–36.
On the need for a theory of wildland fire spread.Crossref | GoogleScholarGoogle Scholar |

Flannigan M, Krawchuk M, De Groot W, Wotton B, Gowman L (2009) Implications of changing climate for global wildland fire. International Journal of Wildland Fire 18, 483–507.
Implications of changing climate for global wildland fire.Crossref | GoogleScholarGoogle Scholar |

Flannigan M, Cantin AS, De Groot WJ, Wotton M, Newbery A, Gowman LM (2013) Global wildland fire season severity in the 21st century. Forest Ecology and Management 294, 54–61.
Global wildland fire season severity in the 21st century.Crossref | GoogleScholarGoogle Scholar |

Gonzalez RC, Woods RE (2008) ‘Digital Image Processing’, 3rd edn. (Pearson Prentice Hall: Upper Saddle River, NJ, USA)

Hemery B, Laurent H, Rosenberger C (2010) Comparative study of localization metrics for the evaluation of image interpretation systems. Journal of Electronic Imaging 19, 023017
Comparative study of localization metrics for the evaluation of image interpretation systems.Crossref | GoogleScholarGoogle Scholar |

Johnston JM, Wooster MJ, Paugam R, Wang X, Lynham TJ, Johnston LM (2017) Direct estimation of Byram’s fire intensity from infrared remote sensing imagery. International Journal of Wildland Fire 26, 668–684.
Direct estimation of Byram’s fire intensity from infrared remote sensing imagery.Crossref | GoogleScholarGoogle Scholar |

Ko BC, Cheong K-H, Nam J-Y (2009) Fire detection based on vision sensor and support vector machines. Fire Safety Journal 44, 322–329.
Fire detection based on vision sensor and support vector machines.Crossref | GoogleScholarGoogle Scholar |

Lentile LB, Holden ZA, Smith AMS, Falkowski MJ, Hudak AT, Morgan P, Lewis SA, Gessler PE, Benson NC (2006) Remote sensing techniques to assess active fire characteristics and post-fire effects. International Journal of Wildland Fire 15, 319–345.
Remote sensing techniques to assess active fire characteristics and post-fire effects.Crossref | GoogleScholarGoogle Scholar |

Mandel J, Bennethum LS, Beezley JD, Coen JL, Douglas CC, Kim M, Vodacek A (2008) A wildland fire model with data assimilation. Mathematics and Computers in Simulation 79, 584–606.
A wildland fire model with data assimilation.Crossref | GoogleScholarGoogle Scholar |

Manzano-Agugliaro F, Pérez-Aranda J, De La Cruz JL (2014) Methodology to obtain isochrones from large wildfires. International Journal of Wildland Fire 23, 338–349.
Methodology to obtain isochrones from large wildfires.Crossref | GoogleScholarGoogle Scholar |

Marr D, Hildreth E (1980) Theory of Edge Detection. Proceedings of the Royal Society of London. Series B, Biological Sciences 207, 187–217.
Theory of Edge Detection.Crossref | GoogleScholarGoogle Scholar | 1:STN:280:DyaL3c7msleqtg%3D%3D&md5=0aed1472f1dc3af8b29eeb446f132089CAS |

Martínez-de Dios JR, Merino L, Caballero F, Ollero A (2011) Automatic forest-fire measuring using ground stations and Unmanned Aerial Systems. Sensors 11, 6328–6353.
Automatic forest-fire measuring using ground stations and Unmanned Aerial Systems.Crossref | GoogleScholarGoogle Scholar |

Medina-Carnicer R, Muñoz-Salinas R, Carmona-Poyato A, Madrid-Cuevas FJ (2011a) A novel histogram transformation to improve the performance of thresholding methods in edge detection. Pattern Recognition Letters 32, 676–693.
A novel histogram transformation to improve the performance of thresholding methods in edge detection.Crossref | GoogleScholarGoogle Scholar |

Medina-Carnicer R, Muñoz-Salinas R, Yeguas-Bolivar E, Diaz-Mas L (2011b) A novel method to look for the hysteresis thresholds for the Canny edge detector. Pattern Recognition 44, 1201–1211.
A novel method to look for the hysteresis thresholds for the Canny edge detector.Crossref | GoogleScholarGoogle Scholar |

Ononye A, Vodacek A, Saber E (2007) Automated extraction of fire line parameters from multispectral infrared images. Remote Sensing of Environment 108, 179–188.
Automated extraction of fire line parameters from multispectral infrared images.Crossref | GoogleScholarGoogle Scholar |

Pastor E, Zarate L, Planas E, Arnaldos J (2003) Mathematical models and calculation systems for the study of wildland fire behaviour. Progress in Energy and Combustion Science 29, 139–153.
Mathematical models and calculation systems for the study of wildland fire behaviour.Crossref | GoogleScholarGoogle Scholar |

Pastor E, Àgueda A, Andrade-Cetto J, Muñoz M, Pérez Y, Planas E (2006) Computing the rate of spread of linear flame fronts by thermal image processing. Fire Safety Journal 41, 569–579.
Computing the rate of spread of linear flame fronts by thermal image processing.Crossref | GoogleScholarGoogle Scholar |

Pastor E, Pérez Y, Cubells M, Planas E, Plucinski M, Gould J (2010) Quantifiable assessment of aerial suppression tactics in wildland fires using airborne infrared imagery. In ‘Proceedings of the VI International Conference on Forest Fire Research’, 15–18 November 2010, Coimbra, Portugal. (Ed. DX Viegas) (CD-ROM) (ADAI: Coimbra, Portugal)

Paugam R, Wooster MJ, Roberts G (2013) Use of handheld thermal imager data for airborne mapping of fire radiative power and energy and flame front rate of spread. IEEE Transactions on Geoscience and Remote Sensing 51, 3385–3399.
Use of handheld thermal imager data for airborne mapping of fire radiative power and energy and flame front rate of spread.Crossref | GoogleScholarGoogle Scholar |

Pausas JG (2004) Changes in fire and climate in the eastern Iberian Peninsula (Mediterranean Basin). Climatic Change 63, 337–350.
Changes in fire and climate in the eastern Iberian Peninsula (Mediterranean Basin).Crossref | GoogleScholarGoogle Scholar |

Peli T, Malah D (1982) A study of edge detection algorithms. Computer Graphics and Image Processing 20, 1–21.
A study of edge detection algorithms.Crossref | GoogleScholarGoogle Scholar |

Pérez Y, Pastor E, Planas E, Plucinski M, Gould J (2011) Computing forest fires aerial suppression effectiveness by IR monitoring. Fire Safety Journal 46, 2–8.
Computing forest fires aerial suppression effectiveness by IR monitoring.Crossref | GoogleScholarGoogle Scholar |

Planas E, Pastor E, Cubells M, Cruz M, Greenfell I (2011) Fire behavior variability in mallee–heath shrubland fires. In ‘The 5th International Wildland Fire Conference’, 9–13 May 2011, Sun City, South Africa.

Plucinski M, Pastor E (2013) Criteria and methodology for evaluating aerial wildfire suppression. International Journal of Wildland Fire 22, 1144–1154.
Criteria and methodology for evaluating aerial wildfire suppression.Crossref | GoogleScholarGoogle Scholar |

Pratt WK (1978) ‘Digital Image Processing.’ (John Wiley & Sons Inc: New York)

Prewitt J (1970) Object enhancement and extraction. In ‘Picture processing and Psychopictorics’. (Eds B. Lipkin and A. Rosenfeld) pp. 75-149. (Academic Press: New York)

Riggan PJ, Tissell RG, Hoffman JW (2003) Application of the FireMapperTM thermal-imaging radiometer for wildfire suppression. IEEE Aerospace Conference Proceedings 4, 1863–1872.
Application of the FireMapperTM thermal-imaging radiometer for wildfire suppression.Crossref | GoogleScholarGoogle Scholar |

Rios O, Jahn W, Rein G (2014) Forecasting wind-driven wildfires using an inverse modelling approach. Natural Hazards and Earth System Sciences 14, 1491–1503.
Forecasting wind-driven wildfires using an inverse modelling approach.Crossref | GoogleScholarGoogle Scholar |

Rios O, Pastor E, Valero MM, Planas E (2016) Short-term fire front spread prediction using inverse modelling and airborne infrared images. International Journal of Wildland Fire 25, 1033–1047.
Short-term fire front spread prediction using inverse modelling and airborne infrared images.Crossref | GoogleScholarGoogle Scholar |

Rochoux MC, Ricci S, Lucor D, Cuenot B, Trouvé A (2014) Towards predictive data-driven simulations of wildfire spread – part I: reduced-cost ensemble Kalman filter based on a polynomial chaos surrogate model for parameter estimation. Natural Hazards and Earth System Sciences 14, 2951–2973.
Towards predictive data-driven simulations of wildfire spread – part I: reduced-cost ensemble Kalman filter based on a polynomial chaos surrogate model for parameter estimation.Crossref | GoogleScholarGoogle Scholar |

Rochoux MC, Emery C, Ricci S, Cuenot B, Trouvé A (2015) Towards predictive data-driven simulations of wildfire spread – part II: ensemble Kalman Filter for the state estimation of a front-tracking simulator of wildfire spread. Natural Hazards and Earth System Sciences 15, 1721–1739.
Towards predictive data-driven simulations of wildfire spread – part II: ensemble Kalman Filter for the state estimation of a front-tracking simulator of wildfire spread.Crossref | GoogleScholarGoogle Scholar |

Rossi L, Molinier T, Akhloufi M, Tison Y, Pieri A (2010) A 3-D vision system for the measurement of the rate of spread and the height of fire fronts. Measurement Science & Technology 21, 105501
A 3-D vision system for the measurement of the rate of spread and the height of fire fronts.Crossref | GoogleScholarGoogle Scholar |

Rossi L, Molinier T, Pieri A, Akhloufi M, Tison Y, Bosseur F (2011) Measurement of the geometric characteristics of a fire front by stereovision techniques on field experiments. Measurement Science & Technology 22, 125504
Measurement of the geometric characteristics of a fire front by stereovision techniques on field experiments.Crossref | GoogleScholarGoogle Scholar |

Rossi L, Molinier T, Akhloufi M, Pieri A, Tison Y (2013) Advanced stereovision system for fire spreading study. Fire Safety Journal 60, 64–72.
Advanced stereovision system for fire spreading study.Crossref | GoogleScholarGoogle Scholar |

Rudz S, Chetehouna K, Séro-Guillaume O, Pastor E, Planas E (2009) Comparison of two methods for estimating fire positions and the rate of spread of linear flame fronts. Measurement Science & Technology 20, 115501
Comparison of two methods for estimating fire positions and the rate of spread of linear flame fronts.Crossref | GoogleScholarGoogle Scholar |

Rudz S, Chetehouna K, Hafiane A, Laurent H, Séro-Guillaume O (2013) Investigation of a novel image segmentation method dedicated to forest fire applications. Measurement Science & Technology 24, 075403
Investigation of a novel image segmentation method dedicated to forest fire applications.Crossref | GoogleScholarGoogle Scholar |

Shakesby RA (2011) Post-wildfire soil erosion in the Mediterranean: review and future research directions. Earth-Science Reviews 105, 71–100.
Post-wildfire soil erosion in the Mediterranean: review and future research directions.Crossref | GoogleScholarGoogle Scholar |

Sobel IE (1970) Camera Models and Machine Perception. Doctoral Dissertation, Stanford University.

Stow DA, Riggan PJ, Storey EJ, Coulter LL (2014) Measuring fire spread rates from repeat pass airborne thermal infrared imagery. Remote Sensing Letters 5, 803–812.
Measuring fire spread rates from repeat pass airborne thermal infrared imagery.Crossref | GoogleScholarGoogle Scholar |

Sullivan AL (2009a) Wildland surface fire spread modelling, 1990–2007. 1. Physical and quasi-physical models. International Journal of Wildland Fire 18, 349–368.
Wildland surface fire spread modelling, 1990–2007. 1. Physical and quasi-physical models.Crossref | GoogleScholarGoogle Scholar |

Sullivan AL (2009b) Wildland surface fire spread modelling, 1990–2007. 2. Empirical and quasi-empirical models. International Journal of Wildland Fire 18, 369–386.
Wildland surface fire spread modelling, 1990–2007. 2. Empirical and quasi-empirical models.Crossref | GoogleScholarGoogle Scholar |

Sullivan AL (2009c) Wildland surface fire spread modelling, 1990–2007. 3. Simulation and mathematical analogue models. International Journal of Wildland Fire 18, 387–403.
Wildland surface fire spread modelling, 1990–2007. 3. Simulation and mathematical analogue models.Crossref | GoogleScholarGoogle Scholar |

Toulouse T, Rossi L, Celik T, Akhloufi M (2016) Automatic fire pixel detection using image processing: a comparative analysis of rule-based and machine learning-based methods. Signal, Image and Video Processing 10, 647–654.
Automatic fire pixel detection using image processing: a comparative analysis of rule-based and machine learning-based methods.Crossref | GoogleScholarGoogle Scholar |

Veraverbeke S, Sedano F, Hook SJ, Randerson JT, Jin Y, Rogers BM (2014) Mapping the daily progression of large wildland fires using MODIS active fire data. International Journal of Wildland Fire 23, 655–667.
Mapping the daily progression of large wildland fires using MODIS active fire data.Crossref | GoogleScholarGoogle Scholar |

Zajkowski TJ, Dickinson MB, Hiers JK, Holley W, Williams BW, Paxton A, Martinez O, Walker GW (2016) Evaluation and use of remotely piloted aircraft systems for operations and research - RxCADRE 2012. International Journal of Wildland Fire 25, 114–128.
Evaluation and use of remotely piloted aircraft systems for operations and research - RxCADRE 2012.Crossref | GoogleScholarGoogle Scholar |