Automatic urban debris zone extraction from post-hurricane very high-resolution satellite and aerial imagery

Abstract

Automated remote sensing methods have not gained widespread usage for damage assessment after hurricane events, especially for low-rise buildings, such as individual houses and small businesses. Hurricane wind, storm surge with waves, and inland flooding have unique damage signatures, further complicating the development of robust automated assessment methodologies. As a step toward realizing automated damage assessment for multi-hazard hurricane events, this paper presents a mono-temporal image classification methodology that quickly and accurately differentiates urban debris from non-debris areas using post-event images. Three classification approaches are presented: spectral, textural, and combined spectralÀtextural. The methodology is demonstrated for Gulfport, Mississippi, using IKONOS panchromatic satellite and NOAA aerial colour imagery collected after 2005 Hurricane Katrina. The results show that multivariate texture information significantly improves debris class detection performance by decreasing the confusion between debris and other land cover types, and the extracted debris zone accurately captures debris distribution. Additionally, the extracted debris boundary is approximately equivalent regardless of imagery type, demonstrating the flexibility and robustness of the debris mapping methodology. While the test case presents results for hurricane hazards, the proposed methodology is generally developed and expected to be effective in delineating debris zones for other natural hazards, including tsunamis, tornadoes, and earthquakes.

Remote Sensing-Based Proxies for Urban Disaster Risk Management and Resilience: A Review

“…Tamkuan and Nagai [68] used similar proxies: cracks, displaced and collapsed roofing tiles, wall mortar that is somewhat peeled off, or inclined buildings ( Figure 3D) to evaluate and classify the building-based damages, e.g., roof tile displacements and inclined buildings are used as proxies for detecting slightly and heavily damaged buildings, respectively. Rubble piles and debris ( Figure 3E) are the first features to draw attention and they have been frequently used as proxies for damage detection [76][77][78][79][80][81], while spalling of buildings ( Figure 3E) also is one of the features for heavy damages which has been used for damage detection with UAV [71,82] and satellite images [75]. Furthermore, geometric deformation of entire buildings, such as changes in building shape and size, is employed as a proxy to extract the partly damaged buildings using satellite images [72].…”

“…Furthermore, debris line acts as a proxy to identify the impact of water related disasters, such as tsunami [102] and hurricane [101]. The debris line demonstrates how far water reached inland after a disaster, and it has also been used to identify debris zone [81].…”

Assessing the Resilience of Coastal Wetlands to Extreme Hydrologic Events Using Vegetation Indices: A Review

“…To detect damage resulting from an event, we typically define threshold values selected from the target attribute's data distribution. Jiang and Friedland [82] presented a mono-temporal image classification methodology using IKONOS panchromatic satellite and NOAA aerial color imagery collected in 2005 after Hurricane Katrina. The classification quickly and accurately differentiated urban debris from non-urban debris using post-event images.…”

Use of aerial multispectral images for spatial analysis of flooded riverbed-alluvial plain systems: the case study of the Paglia River (central Italy)

“…Some examples of automated remote sensing applied to post-event images were used by Jiang and Friedland (2015) to accurately differentiate urban debris areas from non-debris areas. Moreover, the use of remote sensing techniques appears to be fundamental even for flood risk management (Franci et al 2014;Amarnath & Rajah 2015).…”