A QGIS Tool for Automatically Identifying Asbestos Roofing

Exposure to asbestos fibers implies a long-term risk for human health; therefore, the development of information systems that are able to detect the extent and status of asbestos over a certain territory has become a priority. This work presents a tool (based on the geographic information system open source software, QGIS) that is conceived for automatically identifying buildings with asbestos roofing. The area under investigation is the metropolitan area around Prato (Italy). The performance analysis of this system was carried out by classifying images that were acquired by the WorldView-3 sensor. These images are available at a low cost when compared with those obtained by means of aerial surveys, and they provide adequate resolution levels for roofing classification. The tool, a QGIS plugin, has shown fairly good performance in identifying asbestos roofing, with some false negatives and some false positives when applying a per-pixel classification. A performance improvement is obtainable when considering the percentage of asbestos pixels that are contained in each roof of the analyzed image. This value is also available with the plugin. In the future, this tool should make it possible to monitor the asbestos roof removal process over time in the area of interest, in accordance with other image data that give evidence of such removals.

[1]  J. R. Jensen,et al.  Remote Sensing of Urban/Suburban Infrastructure and Socio‐Economic Attributes , 2011 .

[2]  Marco Gianinetto,et al.  Mapping Asbestos-Cement Roofing with Hyperspectral Remote Sensing over a Large Mountain Region of the Italian Western Alps , 2014, Sensors.

[3]  Mahta Moghaddam,et al.  Wetlands map of Alaska using L-Band radar satellite imagery , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[4]  Luca Congedo,et al.  Developing expeditious methodology for mapping asbestos-cement roof coverings over the territory of Lazio Region , 2014 .

[5]  Anton Novichikhin.  Digital Globe , 2021 .

[6]  Fabio Pacifici.  On the predictive value of the WorldView3 VNIR and SWIR spectral bands , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[7]  Marco Gianinetto,et al.  Airborne remote sensing for mapping asbestos roofs in aosta valley , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[8]  Helmi Zulhaidi Mohd Shafri,et al.  Development of a Generic Model for the Detection of Roof Materials Based on an Object-Based Approach Using WorldView-2 Satellite Imagery , 2013 .

[9]  Sarawut Ninsawat,et al.  Identification of roofing materials with Discriminant Function Analysis and Random Forest classifiers on pan-sharpened WorldView-2 imagery – a comparison , 2018, Hungarian Geographical Bulletin.

[10]  V. Cuomo,et al.  Deterioration status of asbestos-cement roofing sheets assessed by analyzing hyperspectral data , 2007 .

[11]  P W J Bartrip,et al.  History of asbestos related disease , 2004, Postgraduate Medical Journal.

[12]  Romania TESTING ALGORITHMS FOR THE IDENTIFICATION OF ASBESTOS ROOFING BASED ON HYPERSPECTRAL DATA , 2015 .

[13]  A COMPARISON BETWEEN METHODS – A SPECIALIZED OPERATOR , OBJECT ORIENTED AND PIXEL-ORIENTED IMAGE ANALYSIS – TO DETECT ASBESTOS COVERAGES IN BUILDING ROOFS USING REMOTELY SENSED DATA , 2008 .

[14]  Sandra Lowe,et al.  Classification Methods For Remotely Sensed Data , 2016 .

[15]  S. Bhaskaran,et al.  Per-pixel and object-oriented classification methods for mapping urban features using Ikonos satellite data , 2010 .

[16]  Mahta Moghaddam,et al.  Mapping vegetated wetlands of Alaska using L-band radar satellite imagery , 2009 .

[17]  Helmi Zulhaidi Mohd Shafri,et al.  Development of spectral indices for roofing material condition status detection using field spectroscopy and WorldView-3 data , 2016 .

[18]  John A. Richards,et al.  Classifier performance and map accuracy , 1996 .

[19]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .

[20]  Micol Rossini,et al.  Mapping of Asbestos Cement Roofs and Their Weathering Status Using Hyperspectral Aerial Images , 2015, ISPRS Int. J. Geo Inf..

[21]  Helmi Zulhaidi Mohd Shafri,et al.  A comparison of hyperspectral data and worldview-2 images to detect impervious surface , 2012, 2012 4th Workshop on Hyperspectral Image and Signal Processing (WHISPERS).

[22]  Patricia Gober,et al.  Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery , 2011, Remote Sensing of Environment.

[23]  A. Kulkarni,et al.  Random Forest Algorithm for Land Cover Classification , 2016 .

[24]  Mark A. Friedl,et al.  Estimating pixel-scale land cover classification confidence using nonparametric machine learning methods , 2001, IEEE Trans. Geosci. Remote. Sens..

[25]  Paolo Gamba,et al.  Spaceborne SAR data for global urban mapping at 30 m resolution using a robust urban extractor , 2015 .

[26]  C. Marino,et al.  Airborne hyperspectral remote sensing applications in urban areas: asbestos concrete sheeting identification and mapping , 2001, IEEE/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas (Cat. No.01EX482).

[27]  Stefano Casciardi,et al.  Method validation for the identification of asbestos–cement roofing , 2012 .

[28]  L. Fiumi.  Evaluation of MIVIS hyperspectral data for mapping covering materials , 2001, IEEE/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas (Cat. No.01EX482).

[29]  Helmi Zulhaidi Mohd Shafri,et al.  New semi-automated mapping of asbestos cement roofs using rule-based object-based image analysis and Taguchi optimization technique from WorldView-2 images , 2017 .

[30]  Zoltán Kovács,et al.  TESTING OF ALGORITHMS FOR THE IDENTIFICATION OF ASBESTOS ROOFING BASED ON HYPERSPECTRAL DATA , 2014 .

[31]  Yasunosuke Suzuki,et al.  Short, thin asbestos fibers contribute to the development of human malignant mesothelioma: pathological evidence. , 2005, International journal of hygiene and environmental health.

[32]  Hurtado Abril,et al.  Generación de un índice espectro-temporal para la identificación de zonas afectadas por deforestación usando imágenes Landsat. , 2020 .