Extensive Exposure Mapping in Urban Areas through Deep Analysis of Street-Level Pictures for Floor Count Determination

Iannelli, Gianni Cristian; Dell’Acqua, Fabio

doi:10.3390/urbansci1020016

Cited by 25 publications

(15 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As described in DECAF [39], it is possible to use a pre-trained ConvNet as feature generator and apply classical machine learning such as Support Vector Machine (SVM) or logistic regression to train a model with good performance. Transfer learning is utilized, such as classification of satellite images [42], vehicles detection based on RGB images or LiDAR data [43,44], visual floor count determination [45] or visual localization [46]. Only recently, this approach was used for retrieving flooding relevant social media photos [27,28].…”

Section: Related Methods For Interpreting Flood Relevant Social Mediamentioning

confidence: 99%

Extraction of Pluvial Flood Relevant Volunteered Geographic Information (VGI) by Deep Learning from User Generated Texts and Photos

Feng

Sester

2018

IJGI

View full text Add to dashboard Cite

Abstract:In recent years, pluvial floods caused by extreme rainfall events have occurred frequently. Especially in urban areas, they lead to serious damages and endanger the citizens' safety. Therefore, real-time information about such events is desirable. With the increasing popularity of social media platforms, such as Twitter or Instagram, information provided by voluntary users becomes a valuable source for emergency response. Many applications have been built for disaster detection and flood mapping using crowdsourcing. Most of the applications so far have merely used keyword filtering or classical language processing methods to identify disaster relevant documents based on user generated texts. As the reliability of social media information is often under criticism, the precision of information retrieval plays a significant role for further analyses. Thus, in this paper, high quality eyewitnesses of rainfall and flooding events are retrieved from social media by applying deep learning approaches on user generated texts and photos. Subsequently, events are detected through spatiotemporal clustering and visualized together with these high quality eyewitnesses in a web map application. Analyses and case studies are conducted during flooding events in Paris, London and Berlin.

show abstract

Section: Related Methods For Interpreting Flood Relevant Social Mediamentioning

confidence: 99%

Extraction of Pluvial Flood Relevant Volunteered Geographic Information (VGI) by Deep Learning from User Generated Texts and Photos

Feng

Sester

2018

IJGI

View full text Add to dashboard Cite

show abstract

“…A study about the use of UAVs for assisting the design of technical measures for a seismic emergency using photogrammetric techniques has been recently published [16], validating the capabilities of UAVs for reducing the operator's risk exposure during the consolidation of the damages that occurred to the building environment and the architectural heritage. The use of building facade images has also been used for the automatic production of "exposure proxy" layers, to be used for determining buildings footprints and their related floor numbers, in order to provide sensible results in risk assessment when a disaster strikes [17]. Moreover, different considerations are proposed in [18] concerning the use of UAVs for post-natural disaster damage evaluation, both for assisting with logistics and cargo delivery, and for performing post-disaster aerial assessments.…”

Section: Use Of Uavs At Post-disaster Construction Sitesmentioning

confidence: 99%

The Use of UAVs for Performing Safety-Related Tasks at Post-Disaster and Non-Critical Construction Sites

Calantropio

2019

Safety

View full text Add to dashboard Cite

Thanks to the wide diffusion of unmanned aerial vehicles (UAVs), geomatics solutions have actively contributed to the field of safety enhancement and disaster risk reduction, supporting rapid mapping and documentation activities of the damages that have occurred to heritage buildings after natural disasters (such as earthquakes) where, in this scenario it is even more important to plan and execute disaster assessment and response operations in safe conditions. In fact, the planning and execution of technical countermeasures in a seismic emergency response involve higher risks for the safety of the operators as compared with responses related to the activities performed at non-critical construction sites. After an analysis of the state of the art, this study aims to underline the possibilities offered by the use of UAVs for performing safety-related tasks, both at post-disaster and non-critical construction sites. First, a survey has been conducted concerning the main user expectations and characteristics that an ideal UAV platform should have in order to perform safety-related tasks at construction sites that are created following the initial emergency phases. The answers that were obtained have been compared with similar studies retrieved from the literature validating previously conducted research. The legislative context is also considered, as it is an important factor that influences the applicability of these platforms and technology. Along with a method for assessing and mitigating the intrinsic risk of using an UAV, the results of a survey submitted to experts in the field of safety at construction sites is also discussed, intending to identify requirements of the ideal platform and the related user expectations. The results are reported, together with a summary of considerations on the use of these strategies in the analyzed contexts.

show abstract

“…Here we specifically focus on crowdsourced geo-tagged and time-stamped street-view imagery. The enormous potential of these images is illustrated by recent applications in the domains of e.g., political preferences [14], income bracket prediction [15], crime rate prediction [16], electric network maintenance [17], transport [18], urban risk assessment [19], and urban greenery and urban trees [20][21][22]. Different platforms and business models coexist to host the growing archives of street level imagery.…”

Section: Street-level Imagerymentioning

confidence: 99%

Crowdsourced Street-Level Imagery as a Potential Source of In-Situ Data for Crop Monitoring

d’Andrimont

Yordanov

Lemoine

et al. 2018

Land

View full text Add to dashboard Cite

New approaches to collect in-situ data are needed to complement the high spatial (10 m) and temporal (5 d) resolution of Copernicus Sentinel satellite observations. Making sense of Sentinel observations requires high quality and timely in-situ data for training and validation. Classical ground truth collection is expensive, lacks scale, fails to exploit opportunities for automation, and is prone to sampling error. Here we evaluate the potential contribution of opportunistically exploiting crowdsourced street-level imagery to collect massive high-quality in-situ data in the context of crop monitoring. This study assesses this potential by answering two questions: (1) what is the spatial availability of these images across the European Union (EU), and (2) can these images be transformed to useful data? To answer the first question, we evaluated the EU availability of street-level images on Mapillary—the largest open-access platform for such images—against the Land Use and land Cover Area frame Survey (LUCAS) 2018, a systematic surveyed sampling of 337,031 points. For 37.78% of the LUCAS points a crowdsourced image is available within a 2 km buffer, with a mean distance of 816.11 m. We estimate that 9.44% of the EU territory has a crowdsourced image within 300 m from a LUCAS point, illustrating the huge potential of crowdsourcing as a complementary sampling tool. After artificial and built up (63.14%), and inland water (43.67%) land cover classes, arable land has the highest availability at 40.78%. To answer the second question, we focus on identifying crops at parcel level using all 13.6 million Mapillary images collected in the Netherlands. Only 1.9% of the contributors generated 75.15% of the images. A procedure was developed to select and harvest the pictures potentially best suited to identify crops using the geometries of 785,710 Dutch parcels and the pictures’ meta-data such as camera orientation and focal length. Availability of crowdsourced imagery looking at parcels was assessed for eight different crop groups with the 2017 parcel level declarations. Parcel revisits during the growing season allowed to track crop growth. Examples illustrate the capacity to recognize crops and their phenological development on crowdsourced street-level imagery. Consecutive images taken during the same capture track allow selecting the image with the best unobstructed view. In the future, dedicated crop capture tasks can improve image quality and expand coverage in rural areas.

show abstract

Extensive Exposure Mapping in Urban Areas through Deep Analysis of Street-Level Pictures for Floor Count Determination

Cited by 25 publications

References 33 publications

Extraction of Pluvial Flood Relevant Volunteered Geographic Information (VGI) by Deep Learning from User Generated Texts and Photos

Extraction of Pluvial Flood Relevant Volunteered Geographic Information (VGI) by Deep Learning from User Generated Texts and Photos

The Use of UAVs for Performing Safety-Related Tasks at Post-Disaster and Non-Critical Construction Sites

Crowdsourced Street-Level Imagery as a Potential Source of In-Situ Data for Crop Monitoring

Contact Info

Product

Resources

About