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

Object-based post-fire aerial image classification for building damage, destruction and defensive actions at the 2012 Colorado Waldo Canyon Fire

Derek McNamara A D , William Mell B and Alexander Maranghides C
+ Author Affiliations
- Author Affiliations

A Geospatial Measurement Solutions, LLC, 2149 Cascade Avenue, Ste 106A PMB 240 Hood River, OR 97031, USA.

B United States Forest Service, 400 North 34th Street, Suite 201 Seattle, WA 98103, USA.

C National Institute of Standards and Technology, 100 Bureau Drive, Gaithersburg, MD 20899-8663, USA.

D Corresponding author. Email: dmgeo@gmsgis.com

International Journal of Wildland Fire 29(2) 174-189 https://doi.org/10.1071/WF19041
Submitted: 26 March 2019  Accepted: 8 November 2019   Published: 24 December 2019

Abstract

We compare the use of post-fire aerial imagery to ground-based assessment for identifying building destruction and damage at the 2012 Colorado Waldo Canyon Fire. We also compare active-fire defensive actions identified via manual and automated post-fire image classification to defensive actions documented from ground-based assessments (witness discussions, vehicle logs and images). For building destruction, manual and automatic image classification compared favourably to ground-based assessment, with low errors of commission (0.0–0.4%) and omission (0–1.2%). For building damage, classifying imagery manually had significant errors of commission and omission (59.0% and 57.9%) because ground-based assessments missed roof damage and image classification excluded interior and side damage, indicating the need for both techniques. Classifying imagery automatically for indicators of active-fire water suppression on buildings has Kappa statistics indicating a substantial agreement with documented water suppression. Manual and automatic image classification underestimated the full extent of documented defensive actions but showed a statistically significant dependence between fire cessation and defensive actions. These results show post-fire imagery to be a useful addition to other techniques for identifying building damage, destruction and defensive actions. Also demonstrated is the importance of accounting for defensive actions and other factors in wildland–urban interface fire studies.

Additional keywords: combustion, fire suppression, firefighters, remote sensing, wildland–urban interface, WUI.


References

Alexandre PM, Stewart SI, Mockrin MH, Keuler NS, Syphard AD, Bar-Massada A, Clayton MK, Radeloff VC (2016) The relative impacts of vegetation, topography and spatial arrangement on building loss to wildfires in case studies of California and Colorado. Landscape Ecology 31, 415–430.
The relative impacts of vegetation, topography and spatial arrangement on building loss to wildfires in case studies of California and Colorado.Crossref | GoogleScholarGoogle Scholar |

Bittner K, Cui S, Reinartz P International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-1/W1, 481–486.

Blanchi R, Leonard J (2008) Property safety: Judging structural safety. In ‘Community Bushfire Safety.’ (Eds J Handmer, K Haynes.) pp. 77–85. (Bushfire Co-operative Research Centre: Melbourne)

Blaschke T (2003) Object-based contextual image classification built on image segmentation. IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data. 27–28 October 2003, Greenbelt, MD.

Caggiano MD, Tinkham WT, Hoffman C, Cheng AS, Hawbaker TJ (2016) High resolution mapping of development in the wildland-urban interface using object based image extraction. Heliyon 2, e00174
High resolution mapping of development in the wildland-urban interface using object based image extraction.Crossref | GoogleScholarGoogle Scholar | 27752649PubMed |

CAL FIRE Incident Management Team 3 (2015) Valley incident Damage Inspection Report: CALNU008670. California Department of Forestry and Fire Protection. Available at https://www.fire.ca.gov/media/5308/j_damage-assessment-report.pdf [Verified 19 November 2019]

Calkin DE, Rieck JD, Hyde KD, Kaiden JD (2011) Built structure identification in wildfire decision support. International Journal of Wildland Fire 20, 78–90.
Built structure identification in wildfire decision support.Crossref | GoogleScholarGoogle Scholar |

City of Colorado Springs (2013) Waldo Canyon Fire 23 June 2012 to 10 July 2012: final after-action report. Available at https://cdpsdocs.state.co.us/coe/Website/Data_Repository/Waldo%20Canyon%20Fire%20Final%20After%20Action%20Report_City%20of%20Colorado%20Springs.pdf [Verified 16 August 2018].

Cohen J (1960) A coefficient of agreement for nominal scales. Educational and Psychological Measurement 20, 37–46.
A coefficient of agreement for nominal scales.Crossref | GoogleScholarGoogle Scholar |

Cohen JD (2000) Preventing disaster: home ignitability in the wildland-urban interface. Journal of Forestry 98, 15–21.

Cohen JD, Stratton RD (2008) Home destruction examination, Grass Valley Fire, Lake Arrowhead, CA. USDA Forest Service, Pacific Southeast Region, Technical Paper R5-TP-026b. (Ogden, UT, USA)

Congalton RC (2001) Accuracy assessment and validation of remotely sensed and other spatial information. International Journal of Wildland Fire 10, 321–328.
Accuracy assessment and validation of remotely sensed and other spatial information.Crossref | GoogleScholarGoogle Scholar |

DigitalGlobe (2018) Open data program. Available at https://www.digitalglobe.com/opendata [Verified 16 August 2018].

GeoCue Group Support (2017a) Planar point filter point cloud task. Available at http://support.geocue.com/planar-point-filter-point-cloud-task/ [Verified 16 August 2018].

GeoCue Group Support (2017b) Point cloud cluster tracing point cloud task. Available at http://support.geocue.com/point-cloud-cluster-tracing-point-cloud-task/ [Verified 16 August 2018].

Gibbons P, Van Bommel L, Gill AM, Cary GJ, Driscoll DA, Bradstock RA, Knight E, Moritz MA, Stephens SL, Lindenmayer DB (2012) Land management practices associated with house loss in wildfires. PLoS One 7, e29212
Land management practices associated with house loss in wildfires.Crossref | GoogleScholarGoogle Scholar | 23227217PubMed |

Henning AH, Cox J, Shew D (2016) Cal FIRE’s damage inspection program: its evolution and implementation. Paper presented at NFPA Conference and Expo, Las Vegas, NV, June 13–16.

Landis J, Koch G (1977) The measurement of observer agreement for categorical data. Biometrics 33, 159–174.
The measurement of observer agreement for categorical data.Crossref | GoogleScholarGoogle Scholar | 843571PubMed |

Manzello SL, Park SH, Thomas GC, Shields JR (2009) Developing rapid response instrumentation packages to quantify structure ignition mechanisms in wildland-urban interface (WUI) fires. Paper presented at Fire and Materials, 11th International Conference and Exhibition (San Francisco, CA)

Maranghides A, McNamara D (2016) 2011 Wildland-urban interface Amarillo fires report #2 – assessment of fire behavior and WUI measurement science. National Institute of Standards and Technology Technical Note 1909. (Gaithersburg, MD). Available at https://nvlpubs.nist.gov/nistpubs/TechnicalNotes/NIST.TN.1909.pdf [Verified 18 November 2019]

Maranghides A, Mell W (2011) A case study of a community affected by the Witch and Guejito wildland fires. Fire Technology 47, 379–420.
A case study of a community affected by the Witch and Guejito wildland fires.Crossref | GoogleScholarGoogle Scholar |

Maranghides A, McNamara D, Vihnanek R, Restaino J, Leland C (2015) A case study of a community affected by the Waldo Fire: event timeline and defensive actions. National Institute of Standards and Technology Technical Note 1910. (Gaithersburg, MD) Available at https://nvlpubs.nist.gov/nistpubs/TechnicalNotes/NIST.TN.1910.pdf [Verified 18 November 2019]

Penman SH, Price OF, Penman TD, Bradstock RA (2019) The role of defensible space on the likelihood of house impact from wildfires in forested landscapes of south eastern Australia. International Journal of Wildland Fire 28, 4–14.
The role of defensible space on the likelihood of house impact from wildfires in forested landscapes of south eastern Australia.Crossref | GoogleScholarGoogle Scholar |

Quarles S, Leschak P, Cowger R, Brown R, Iskowitz C (2013) Lessons learned from Waldo Canyon: Fire Adapted Communities mitigation assessment team findings. Insurance Institute for Business & Home Safety. Available at https://fireadapted.org/wp-content/uploads/2018/06/waldo-canyon-report.pdf [Verified 18 November 2019]

Regional Municipality of Wood Buffalo (2017) Fire assessment tool. Available at http://firemap.rmbwb.ca. [Verified 16 August 2018].

Restas A (2015) Drone applications for supporting disaster management. World Journal of Engineering and Technology 3, 316–321.
Drone applications for supporting disaster management.Crossref | GoogleScholarGoogle Scholar |

Syphard AD, Keeley JE, Bar-Massada A, Brennan TJ, Radeloff VC (2012) Housing arrangement and location determine the likelihood of housing loss due to wildfire. PLoS One 7, e33954
Housing arrangement and location determine the likelihood of housing loss due to wildfire.Crossref | GoogleScholarGoogle Scholar | 22623955PubMed |

Syphard AD, Brennan TJ, Keeley JE (2014) The role of defensible space for residential structure protection during wildfires. International Journal of Wildland Fire 23, 1165–1175.
The role of defensible space for residential structure protection during wildfires.Crossref | GoogleScholarGoogle Scholar |

Whittaker J, Haynes K, Handmer J, McLennan J (2013) Community safety during the 2009 Australian ‘Black Saturday’ bushfires: an analysis of household preparedness and response. International Journal of Wildland Fire 22, 841–849.
Community safety during the 2009 Australian ‘Black Saturday’ bushfires: an analysis of household preparedness and response.Crossref | GoogleScholarGoogle Scholar |

Xu Y, Wu L, Xie Z, Chen Z (2018) Building extraction in very high-resolution remote sensing imagery using deep learning and guide filters. Remote Sensing 10, 144
Building extraction in very high-resolution remote sensing imagery using deep learning and guide filters.Crossref | GoogleScholarGoogle Scholar |