Identifying elements that affect the probability of buildings to suffer flooding in urban areas using Google Street View. A case study from Athens metropolitan area in Greece

Diakakis, Michalis; Deligiannakis, Georgios; Pallikarakis, Aggelos; Skordoulis, Michalis

doi:10.1016/j.ijdrr.2017.02.002

Cited by 26 publications

(26 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CS evaluates the building conditions and the degree of degradation, being frequently referred to as relevant in the resistance of structures when affected by a natural hazard (Blanco‐Vogt & Schanze, 2014; Diakakis, Deligiannakis, Pallikarakis, & Skordoulis, 2017; Fedeski & Gwilliam, 2007; Kappes et al, 2012; Papathoma‐Köhle, 2016; Silva & Pereira, 2014; Stephenson & D'Ayala, 2014). This indicator is highly relevant in the study area because of the characteristics of a set of precarious residential buildings.…”

Section: Methodsmentioning

confidence: 99%

Physical vulnerability assessment to flash floods using an indicator‐based methodology based on building properties and flow parameters

Leal

Reis

Pereira

et al. 2021

J Flood Risk Management

View full text Add to dashboard Cite

This study focuses on the physical vulnerability of buildings to flash floods using an indicator‐based methodology. A physical vulnerability index (PhVI) that combines intrinsic vulnerability (IV) of buildings and flash flood intensity (FFI) is proposed. IV evaluates the propensity to suffer damage, resulting from indicators related to building properties. FFI estimates the potential to cause damage, resulting from indicators related to flow parameters. PhVI was applied to a critical section of a small drainage basin in Portugal where flash floods are frequent. Evaluating IV and the intensity of natural hazards is essential in physical vulnerability assessments. This study addresses two problems found in the literature: the lack of flash flood‐dedicated physical vulnerability assessments and the difficulties in assembling building properties and the intensity of natural hazards in a vulnerability index defined from indicator‐based methodologies. PhVI is a useful tool where damage records are rare or non‐existent, allowing the prioritisation of resources and application of local protection measures. This index can be adapted to other study areas and natural hazards, although more research is needed to improve the knowledge on the indicators and weights of IV and FFI.

show abstract

Section: Methodsmentioning

confidence: 99%

Physical vulnerability assessment to flash floods using an indicator‐based methodology based on building properties and flow parameters

Leal

Reis

Pereira

et al. 2021

J Flood Risk Management

View full text Add to dashboard Cite

show abstract

“…De Vitry et al [10] used a deep convolutional neural network to detect floodwater in surveillance footage and proposed a novel qualitative flood index to monitor flood level trends. Diakakis et al [11] used Google Street View to manually detect buildings that have been flooded. Schnebele et al [12] used video data for a visual assessment of flood hazards.…”

Section: Introductionmentioning

confidence: 99%

Obtaining Urban Waterlogging Depths from Video Images Using Synthetic Image Data

Jiang

Qin

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Reference objects in video images can be used to indicate urban waterlogging depths. The detection of reference objects is the key step to obtain waterlogging depths from video images. Object detection models with convolutional neural networks (CNNs) have been utilized to detect reference objects. These models require a large number of labeled images as the training data to ensure the applicability at a city scale. However, it is hard to collect a sufficient number of urban flooding images containing valuable reference objects, and manually labeling images is time-consuming and expensive. To solve the problem, we present a method to synthesize image data as the training data. Firstly, original images containing reference objects and original images with water surfaces are collected from open data sources, and reference objects and water surfaces are cropped from these original images. Secondly, the reference objects and water surfaces are further enriched via data augmentation techniques to ensure the diversity. Finally, the enriched reference objects and water surfaces are combined to generate a synthetic image dataset with annotations. The synthetic image dataset is further used for training an object detection model with CNN. The waterlogging depths are calculated based on the reference objects detected by the trained model. A real video dataset and an artificial image dataset are used to evaluate the effectiveness of the proposed method. The results show that the detection model trained using the synthetic image dataset can effectively detect reference objects from images, and it can achieve acceptable accuracies of waterlogging depths based on the detected reference objects. The proposed method has the potential to monitor waterlogging depths at a city scale.

show abstract

“…Their use in various fields of academic research is constantly increasing. Using virtual surveying techniques and algorithms, OD photo chains have been used in: urban search and rescue (Zhang et al, 2006); data collection of built environment characteristics affecting healthrelated behaviors (Wilson et al, 2012); damage data collection of flood affected buildings (Diakakis et al, 2017) identification of land use types (Zhang et al, 2017); classification of environmental indicators (Clarke et al, 2010); studies on the extent of tree cover (Berland and Lange, 2017); determination of cycling (Badland et al, 2010), car, or pedestrian safety (Yin et al, 2015); surveys of neighborhood crime (Rundle et al, 2011;Mooney et al, 2014;He et al, 2017) or health indicators (Odgers et al, 2012); and assessment of seismic vulnerability of structures (Pittore and Wieland, 2013;Stone et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Earthquake Damage Data Collection Using Omnidirectional Imagery

Stone

Putrino

D’Ayala

2018

Front. Built Environ.

View full text Add to dashboard Cite

The unique perspectives and viewpoints offered by omnidirectional camera technology has the potential to help improve the outcomes of technical post-earthquake reconnaissance missions. Omnidirectional imagery can be used to virtually "walk through" damaged streets post hoc with a 360 • , immersive view. A common reconnaissance mission aim is to accurately collect damage data; however, there are time challenges for surveyors in the field. The manuscript explores the potential for using omnidirectional imagery to improve damage surveying, firstly by comparing results from damage surveys completed in the field with results obtained using omnidirectional images collected during a mission and surveyed by an experienced engineer virtually and secondly by comparing damage assessment obtained through omnidirectional imagery collected on the ground with the EU Copernicus damage assessment maps. The omnidirectional imagery data was collected during two separate Earthquake Engineering Field Investigation Team post-earthquake reconnaissance missions, namely the area affected by the 2016, 7.8 Muisne Earthquake in Ecuador and the area struck by the 2016, 6.2 Amatrice earthquake in Italy. Notwithstanding the diverse geographic scale, terrain and urban context of the two reconnaissance missions, the results consistently show significant capabilities for this technology in the identification of construction typologies, number of stories, aggregated "low" and "high" damage grades, and failure modes. The work highlights potential issues with correct identification of disaggregated lower damage grades (e.g., European Macroseismic Scale (EMS-98) damage grades 0-3). Challenges identified in the virtual survey process included poor image quality, insufficient photo sphere captures, and obstructions such as trees, walls or vehicles. The omnidirectional imagery represents a substantial improvement in damage assessment accuracy in respect to satellite imagery, especially for lower damage grades, while it is an essential tool for comprehensive surveys in reduced access zones with high levels of damage.

show abstract

Identifying elements that affect the probability of buildings to suffer flooding in urban areas using Google Street View. A case study from Athens metropolitan area in Greece

Cited by 26 publications

References 31 publications

Physical vulnerability assessment to flash floods using an indicator‐based methodology based on building properties and flow parameters

Physical vulnerability assessment to flash floods using an indicator‐based methodology based on building properties and flow parameters

Obtaining Urban Waterlogging Depths from Video Images Using Synthetic Image Data

Earthquake Damage Data Collection Using Omnidirectional Imagery

Contact Info

Product

Resources

About