Building Façade Recognition Using Oblique Aerial Images

Yang, Xiucheng; Qin, Xuebin; Wang, Jun; Wang, Jianhua; Ye, Xin; Qin, Qiming

doi:10.3390/rs70810562

Cited by 24 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With the development of airborne oblique photogrammetry, many methods were proposed for detecting windows from aerial images. Yang et al [21] extracted facade regions using straight line segments based on a multi-level feature extraction procedure. The method is severely affected by the detection accuracy of the line segments.…”

Section: A Image-based Methodsmentioning

confidence: 99%

Saliency-Guided Repetition Detection From Facade Point Clouds

et al. 2019

View full text Add to dashboard Cite

We present a saliency-guided algorithm for detecting the locations of repetitive structures on building facades. First, the global and local saliencies of each point are determined by measuring the global rarity and the local distinctness. The saliency map is utilized to adaptively extract the salient points. Second, the salient points are vertically sliced. A curve can be derived by counting the total number of points in each slice. Then, the curve is converted into a square wave to locate the vertical splitting position. Next, each segment is horizontally sliced, similar to the vertical splitting. The salient points are partitioned into repetitive candidates after the vertical and horizontal splitting. Finally, the repetitive candidates are refined according to the similarity of the neighborhood and the regularity of the arrangement. The experimental results demonstrate that our method can quickly and effectively extract repetitions from facade point clouds.

show abstract

Section: A Image-based Methodsmentioning

confidence: 99%

Saliency-Guided Repetition Detection From Facade Point Clouds

et al. 2019

View full text Add to dashboard Cite

show abstract

“…From the perspective of the recognition rate [ 24 ], precision is the percentage of building objects that are correctly classified by the SVM classifier. Recall is the percentage of correctly classified building objects among all actual buildings.…”

Section: Methodsmentioning

confidence: 99%

Feature Selection Method Based on High-Resolution Remote Sensing Images and the Effect of Sensitive Features on Classification Accuracy

Zhou

Zhang

Wang

et al. 2018

Sensors

View full text Add to dashboard Cite

With the advent of high spatial resolution remote sensing imagery, numerous image features can be utilized. Applying a reasonable feature selection approach is critical to effectively reduce feature redundancy and improve the efficiency and accuracy of classification. This paper proposes a novel feature selection approach, in which ReliefF, genetic algorithm, and support vector machine (RFGASVM) are integrated to extract buildings. We adopt the ReliefF algorithm to preliminary filter high-dimensional features in the feature database. After eliminating the sorted features, the feature subset and the C and γ parameters of support vector machine (SVM) are encoded into the chromosome of the genetic algorithm. A fitness function is constructed considering the sample identification accuracy, the number of selected features, and the feature cost. The proposed method was applied to high-resolution images obtained from different sensors, GF-2, BJ-2, and unmanned aerial vehicles (UAV). The confusion matrix, precision, recall and F1-score were applied to assess the accuracy. The results showed that the proposed method achieved feature reduction, and the overall accuracy (OA) was more than 85%, with Kappa coefficient values of 0.80, 0.83 and 0.85, respectively. The precision of each image was more than 85%. The time efficiency of the proposed method was two-fold greater than SVM with all the features. The RFGASVM method has the advantages of large feature reduction and high extraction performance and can be applied in feature selection.

show abstract

“…O dispositivo selecionado para a coleta das imagens aéreas foi o VANT Phantom 4 Pro V 2.0 com a câmera digital embarcada CMOS 1" 20 MP, ambos fabricados pela DJI ( A principal característica do posicionamento das câmeras para as tomadas fotográficas foi o paralelismo entre si, procurando sempre a perpendicularidade ao plano da fachada estudada (MELO JUNIOR, 2016;YANG et al, 2015), sendo recomendável garantir uma sobreposição entre fotografias de 60-80%, tanto longitudinal quanto lateral (GROETELAARS; AMORIM, 2012), além de manter uma relação da distância entre a posição das estações na tomada fotográfica e a distância das estações para a fachada fotografada entre 0,1 e 0,5, pois, se for muito pequena, a correlação automática dos pontos é facilitada, mas a precisão geométrica na reconstrução digital da fachada é prejudicada (PIERROT-DESEILLIGNY; DE LUCA; REMONDINO, 2011).…”

Section: Pré-execução: Análise Do Projetounclassified

Veículos Aéreos Não Tripulados (VANT) para inspeção de manifestações patológicas em fachadas com revestimento cerâmico

Ballesteros

Lordsleem

2021

Ambient. constr.

View full text Add to dashboard Cite

Resumo O mundo passa por uma revolução de ordem abrangente, destacando-se a demanda por inserção tecnológica nos processos industriais, notadamente pela necessidade da otimização do tempo. Em especial, os veículos aéreos não tripulados (VANT), ou “drones”, estão tendo crescente relevância como novo mecanismo de obtenção de dados e inspeções visuais, mais ágeis e seguros. Este artigo teve o objetivo de realizar o estudo experimental do uso de VANT como ferramenta visual para inspeção de manifestações patológicas em fachadas de edifícios. A metodologia contemplou a realização de dois estudos de caso em edificações de mediana e grande altura, em que foram contempladas as etapas de coleta de imagens e processamento. Os resultados da pesquisa exibiram a viabilidade técnica e a eficácia da inspeção, e mostraram que entre os ativos visuais produzidos as fotografias digitais geradas pela aeronave foram mais efetivas para a detecção de manifestações patológicas quando comparadas com os modelos gerados pelo software Agisoft PhotoScan. Como principal contribuição, têm-se a validação do pacote tecnológico destinado a auxiliar no diagnóstico de manifestações patológicas a partir da formulação do protocolo para a inspeção de fachadas com uso de VANT e a análise comparativa dos ativos visuais que podem ser gerados.

show abstract

Building Façade Recognition Using Oblique Aerial Images

Cited by 24 publications

References 19 publications

Saliency-Guided Repetition Detection From Facade Point Clouds

Saliency-Guided Repetition Detection From Facade Point Clouds

Feature Selection Method Based on High-Resolution Remote Sensing Images and the Effect of Sensitive Features on Classification Accuracy

Veículos Aéreos Não Tripulados (VANT) para inspeção de manifestações patológicas em fachadas com revestimento cerâmico

Contact Info

Product

Resources

About