Retrieval of the Height of Buildings From WorldView-2 Multi-Angular Imagery Using Attribute Filters and Geometric Invariant Moments

Licciardi, Giorgio; Villa, Alberto; Mura, Mauro Dalla; Bruzzone, Lorenzo; Chanussot, Jocelyn; Benediktsson, Jón Atli

doi:10.1109/jstars.2012.2184269

Cited by 37 publications

(17 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Different techniques take advantage of specific acquisition techniques such as Light Detection and Ranging (LiDAR), or optical stereo images, to build a Digital Terrain Model (DTM) and a Digital Surface Model (DSM), and to then derive the heights of buildings [5,6]. Another possible set of techniques make use of multiple optical views and template matching algorithms [7,8]. Oblique airborne imagery has also been considered in other efforts [9].…”

Section: Existing Approaches To Floor Number Determinationmentioning

confidence: 99%

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

Iannelli¹,

Dell’Acqua

2017

Urban Science

View full text Add to dashboard Cite

Abstract:In order for a risk assessment to deliver sensible results, exposure in the concerned area must be known or at least estimated in a reliable manner. Exposure estimation, though, may be tricky, especially in urban areas, where large-scale surveying is generally expensive and impractical; yet, it is in urban areas that most assets are at stake when a disaster strikes. Authoritative sources such as cadastral data and business records may not be readily accessible to private stakeholders such as insurance companies; airborne and especially satellite-based Earth-Observation data obviously cannot retrieve all relevant pieces of information. Recently, a growing interest is recorded in the exploitation of street-level pictures, procured either through crowdsourcing or through specialized services like Google Street View. Pictures of building facades convey a great amount of information, but their interpretation is complex. Recently, however, smarter image analysis methods based on deep learning started appearing in literature, made possible by the increasing availability of computational power. In this paper, we leverage such methods to design a system for large-scale, systematic scanning of street-level pictures intended to map floor numbers in urban buildings. Although quite simple, this piece of information is a relevant exposure proxy in risk assessment. In the proposed system, a series of georeferenced images are automatically retrieved from the repository where they sit. A tailored deep learning net is first trained on sample images tagged through visual interpretation, and then systematically applied to the entire retrieved dataset. A specific algorithm allows attaching "number of floors" tags to the correct building in a dedicated GIS (Geographic Information System) layer, which is finally output by the system as an "exposure proxy" layer.

show abstract

Section: Existing Approaches To Floor Number Determinationmentioning

confidence: 99%

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

Iannelli¹,

Dell’Acqua

2017

Urban Science

View full text Add to dashboard Cite

show abstract

“…HU [25] apresentou em sua teoria, uma possibilidade capaz de realizar a descrição de figuras geomé-tricas planas com base nos momentos invariantes bidimensionais [26,27,28].…”

Section: Extração De Característicasunclassified

Classificaçâo automatica do tipo de ferro fundido utilizando reconhecimento de padrões em imagens de microscopia

et al. 2017

View full text Add to dashboard Cite

RESUMOOs ferros fundidos possuem uma microestrutura, na qual, o formato da grafita presente tem direta influência na classificação entre os diversos tipos deste material. A classificação é feita, tradicionalmente, a partir da análise visual realizada por um especialista através do auxílio de um microscópio ótico. O presente trabalho propõe a utilização da Inteligência Computacional Aplicada em conjunto com extratores de informações em imagens de metalografia. A finalidade é auxiliar profissionais da área das Ciências dos Materiais na classificação de ferros fundidos de maneira automática e reduzir o tempo de classificação, restringindo o máximo possível as falhas presentes durante a classificação. Foram realizadas duas etapas para a análise. Na primeira foram consideradas as grafitas separadamente. Em uma segunda etapa, a imagem completa foi analisada considerando todas as grafitas extraídas da mesma, em que o tipo de objeto com maior incidência na análise seria o reconhecimento adotado para toda a amostra. Em ambas as etapas o classificador Support Vector Machine obteve os melhores resultados no reconhecimento do tipo de ferro fundido, com resultados próximos a 100%, e com redução média do tempo de classificação em 92%. Tanto os resultados como o tempo das classificações são comparados com a análise do especialista, como também aos resultados obtidos em classificações do ferro fundido que utilizam uma abordagem com redes neurais e uma classificação supervisionada utilizando apenas os descritores de forma. A partir dos resultados apresentados, conclui-se que a abordagem é promissora podendo incorporar softwares comerciais para auxiliar especialistas da área. Palavras-chave:Ferro fundido, Processamento Digital de Imagens, Reconhecimento de Padrões, Inteligên-cia Computacional Aplicada. ABSTRACTThe cast iron has a microstructure in which the shape of the contained graphite has direct influence in the classification between the several types of this material. The classification is usually made through a visual analysis performed by a specialist using an optical microscope. This work proposes the use of Applied Computational Intelligence in conjunction with extractors of information in metallographic images. The purpose is to assist professionals in the field of Materials Science in the classification of cast iron automatically and reduce the time for classification, restricting as much as possible the faults presented during classification. Two steps were performed for the analysis. In the first one we considered the graphites separately. In a second step, we analyzed the complete image considering all the graphite extracted from it, in which the type of object with greater incidence in the analysis would be the recognition adopted for the whole sample. In both steps, the classifier Support Vector Machine obtained the best results in the recognition of the type of cast iron, with results close to 100%, with a mean reduction of the classification time by 92%. Both the results and the time of the classifications are ...

show abstract

“…Most of these methods (Brunn and Weidner, 1997;San and Turker, 2007;Tian et al, 2014) obtain building height from stereoextracted digital surface model (DSM) by subtracting the digital terrain model (DTM) without above-ground objects. Building heights can also be calculated using the parallax method (Lemoine et al, 2012), attribute filters and geometric invariant moments method (Licciardi et al, 2012), and other methods (Haala and Kada, 2010).…”

Section: Introductionmentioning

confidence: 99%

Impact of Building Heights on 3d Urban Density Estimation From Spaceborne Stereo Imagery

Peng

Gong

Wang

et al. 2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:In urban planning and design applications, visualization of built up areas in three dimensions (3D) is critical for understanding building density, but the accurate building heights required for 3D density calculation are not always available. To solve this problem, spaceborne stereo imagery is often used to estimate building heights; however estimated building heights might include errors. These errors vary between local areas within a study area and related to the heights of the building themselves, distorting 3D density estimation. The impact of building height accuracy on 3D density estimation must be determined across and within a study area. In our research, accurate planar information from city authorities is used during 3D density estimation as reference data, to avoid the errors inherent to planar information extracted from remotely sensed imagery. Our experimental results show that underestimation of building heights is correlated to underestimation of the Floor Area Ratio (FAR). In local areas, experimental results show that land use blocks with low FAR values often have small errors due to small building height errors for low buildings in the blocks; and blocks with high FAR values often have large errors due to large building height errors for high buildings in the blocks. Our study reveals that the accuracy of 3D density estimated from spaceborne stereo imagery is correlated to heights of buildings in a scene; therefore building heights must be considered when spaceborne stereo imagery is used to estimate 3D density to improve precision.

show abstract

Retrieval of the Height of Buildings From WorldView-2 Multi-Angular Imagery Using Attribute Filters and Geometric Invariant Moments

Cited by 37 publications

References 26 publications

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

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

Classificaçâo automatica do tipo de ferro fundido utilizando reconhecimento de padrões em imagens de microscopia

Impact of Building Heights on 3d Urban Density Estimation From Spaceborne Stereo Imagery

Contact Info

Product

Resources

About