Automated image-based identification and consistent classification of fire patterns with quantitative shape analysis and spatial location identification
Fire patterns, consisting of fire effects that offer insights into fire behavior and origin, are currently classified based on investigators' visual observations, leading to subjective interpretations. This study proposes a quantitative fire pattern classification framework to support fire inve...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Developments in the Built Environment |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666165925000122 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542424093687808 |
|---|---|
| author | Pengkun Liu Shuna Ni Stoliarov Stanislav I Pingbo Tang |
| author_facet | Pengkun Liu Shuna Ni Stoliarov Stanislav I Pingbo Tang |
| author_sort | Pengkun Liu |
| collection | DOAJ |
| description | Fire patterns, consisting of fire effects that offer insights into fire behavior and origin, are currently classified based on investigators' visual observations, leading to subjective interpretations. This study proposes a quantitative fire pattern classification framework to support fire investigators, aiming for consistency and accuracy. The framework integrates four components. First, it leverages human-computer interaction to extract fire patterns from surfaces, combining investigator expertise with computational analysis. Second, it employs an aspect ratio-based random forest model to classify fire pattern shapes. Third, fire scene point cloud segmentation enables identification of fire-affected areas and mapping 2D fire patterns to 3D scenes for spatial relationships analysis. Lastly, spatial relationships between fire patterns and elements support an interpretation of fire scenes. These components provide pattern analysis that synthesizes qualitative and quantitative data. The framework's fire pattern shape classification results achieve 93% precision on synthetic data and 83% on real fire patterns. |
| format | Article |
| id | doaj-art-14649d92805e47638924bec0e83dfde6 |
| institution | Kabale University |
| issn | 2666-1659 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Developments in the Built Environment |
| spelling | doaj-art-14649d92805e47638924bec0e83dfde62025-02-04T04:10:36ZengElsevierDevelopments in the Built Environment2666-16592025-03-0121100612Automated image-based identification and consistent classification of fire patterns with quantitative shape analysis and spatial location identificationPengkun Liu0Shuna Ni1Stoliarov Stanislav I2Pingbo Tang3Department of Civil and Environmental Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA, 15213, United StatesDepartment of Fire Protection Engineering, University of Maryland at College Park, 4356 Stadium Drive, College Park, MD, 20742, United StatesDepartment of Fire Protection Engineering, University of Maryland at College Park, 4356 Stadium Drive, College Park, MD, 20742, United StatesDepartment of Civil and Environmental Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA, 15213, United States; Corresponding author.Fire patterns, consisting of fire effects that offer insights into fire behavior and origin, are currently classified based on investigators' visual observations, leading to subjective interpretations. This study proposes a quantitative fire pattern classification framework to support fire investigators, aiming for consistency and accuracy. The framework integrates four components. First, it leverages human-computer interaction to extract fire patterns from surfaces, combining investigator expertise with computational analysis. Second, it employs an aspect ratio-based random forest model to classify fire pattern shapes. Third, fire scene point cloud segmentation enables identification of fire-affected areas and mapping 2D fire patterns to 3D scenes for spatial relationships analysis. Lastly, spatial relationships between fire patterns and elements support an interpretation of fire scenes. These components provide pattern analysis that synthesizes qualitative and quantitative data. The framework's fire pattern shape classification results achieve 93% precision on synthetic data and 83% on real fire patterns.http://www.sciencedirect.com/science/article/pii/S2666165925000122Fire pattern classificationQuantitative shape assessmentPoint cloud segmentationSpatial relationship analyses |
| spellingShingle | Pengkun Liu Shuna Ni Stoliarov Stanislav I Pingbo Tang Automated image-based identification and consistent classification of fire patterns with quantitative shape analysis and spatial location identification Developments in the Built Environment Fire pattern classification Quantitative shape assessment Point cloud segmentation Spatial relationship analyses |
| title | Automated image-based identification and consistent classification of fire patterns with quantitative shape analysis and spatial location identification |
| title_full | Automated image-based identification and consistent classification of fire patterns with quantitative shape analysis and spatial location identification |
| title_fullStr | Automated image-based identification and consistent classification of fire patterns with quantitative shape analysis and spatial location identification |
| title_full_unstemmed | Automated image-based identification and consistent classification of fire patterns with quantitative shape analysis and spatial location identification |
| title_short | Automated image-based identification and consistent classification of fire patterns with quantitative shape analysis and spatial location identification |
| title_sort | automated image based identification and consistent classification of fire patterns with quantitative shape analysis and spatial location identification |
| topic | Fire pattern classification Quantitative shape assessment Point cloud segmentation Spatial relationship analyses |
| url | http://www.sciencedirect.com/science/article/pii/S2666165925000122 |
| work_keys_str_mv | AT pengkunliu automatedimagebasedidentificationandconsistentclassificationoffirepatternswithquantitativeshapeanalysisandspatiallocationidentification AT shunani automatedimagebasedidentificationandconsistentclassificationoffirepatternswithquantitativeshapeanalysisandspatiallocationidentification AT stoliarovstanislavi automatedimagebasedidentificationandconsistentclassificationoffirepatternswithquantitativeshapeanalysisandspatiallocationidentification AT pingbotang automatedimagebasedidentificationandconsistentclassificationoffirepatternswithquantitativeshapeanalysisandspatiallocationidentification |