Automatic Building Height Estimation: Machine Learning Models for Urban Image Analysis
Artificial intelligence (AI) is delivering major advances in the construction engineering sector in this era of building information modelling, applying data collection techniques based on urban image analysis. In this study, building heights were calculated from street-view imagery based on a seman...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/8/5037 |
| _version_ | 1797606483210272768 |
|---|---|
| author | Miguel Ureña-Pliego Rubén Martínez-Marín Beatriz González-Rodrigo Miguel Marchamalo-Sacristán |
| author_facet | Miguel Ureña-Pliego Rubén Martínez-Marín Beatriz González-Rodrigo Miguel Marchamalo-Sacristán |
| author_sort | Miguel Ureña-Pliego |
| collection | DOAJ |
| description | Artificial intelligence (AI) is delivering major advances in the construction engineering sector in this era of building information modelling, applying data collection techniques based on urban image analysis. In this study, building heights were calculated from street-view imagery based on a semantic segmentation machine learning model. The model has a fully convolutional architecture and is based on the HRNet encoder and ResNexts depth separable convolutions, achieving fast runtime and state-of-the-art results on standard semantic segmentation tasks. Average building heights on a pilot German street were satisfactorily estimated with a maximum error of 3 m. Further research alternatives are discussed, as well as the difficulties of obtaining valuable training data to apply these models in countries with no training datasets and different urban conditions. This line of research contributes to the characterisation of buildings and the estimation of attributes essential for the assessment of seismic risk using automatically processed street-view imagery. |
| first_indexed | 2024-03-11T05:15:49Z |
| format | Article |
| id | doaj.art-4698e5962fb54fa4ba239702f8cd41b8 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T05:15:49Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4698e5962fb54fa4ba239702f8cd41b82023-11-17T18:12:48ZengMDPI AGApplied Sciences2076-34172023-04-01138503710.3390/app13085037Automatic Building Height Estimation: Machine Learning Models for Urban Image AnalysisMiguel Ureña-Pliego0Rubén Martínez-Marín1Beatriz González-Rodrigo2Miguel Marchamalo-Sacristán3Department of Land Morphology and Engineering, Civil Engineering School, Universidad Politécnica de Madrid, 28040 Madrid, SpainDepartment of Land Morphology and Engineering, Civil Engineering School, Universidad Politécnica de Madrid, 28040 Madrid, SpainDepartment of Environmental and Forestry Engineering and Management, Civil Engineering School, Universidad Politécnica de Madrid, 28040 Madrid, SpainDepartment of Land Morphology and Engineering, Civil Engineering School, Universidad Politécnica de Madrid, 28040 Madrid, SpainArtificial intelligence (AI) is delivering major advances in the construction engineering sector in this era of building information modelling, applying data collection techniques based on urban image analysis. In this study, building heights were calculated from street-view imagery based on a semantic segmentation machine learning model. The model has a fully convolutional architecture and is based on the HRNet encoder and ResNexts depth separable convolutions, achieving fast runtime and state-of-the-art results on standard semantic segmentation tasks. Average building heights on a pilot German street were satisfactorily estimated with a maximum error of 3 m. Further research alternatives are discussed, as well as the difficulties of obtaining valuable training data to apply these models in countries with no training datasets and different urban conditions. This line of research contributes to the characterisation of buildings and the estimation of attributes essential for the assessment of seismic risk using automatically processed street-view imagery.https://www.mdpi.com/2076-3417/13/8/5037artificial intelligencesemantic segmentationconvolutional neural networksbuilding height estimationseismic exposurestreet view imagery |
| spellingShingle | Miguel Ureña-Pliego Rubén Martínez-Marín Beatriz González-Rodrigo Miguel Marchamalo-Sacristán Automatic Building Height Estimation: Machine Learning Models for Urban Image Analysis Applied Sciences artificial intelligence semantic segmentation convolutional neural networks building height estimation seismic exposure street view imagery |
| title | Automatic Building Height Estimation: Machine Learning Models for Urban Image Analysis |
| title_full | Automatic Building Height Estimation: Machine Learning Models for Urban Image Analysis |
| title_fullStr | Automatic Building Height Estimation: Machine Learning Models for Urban Image Analysis |
| title_full_unstemmed | Automatic Building Height Estimation: Machine Learning Models for Urban Image Analysis |
| title_short | Automatic Building Height Estimation: Machine Learning Models for Urban Image Analysis |
| title_sort | automatic building height estimation machine learning models for urban image analysis |
| topic | artificial intelligence semantic segmentation convolutional neural networks building height estimation seismic exposure street view imagery |
| url | https://www.mdpi.com/2076-3417/13/8/5037 |
| work_keys_str_mv | AT miguelurenapliego automaticbuildingheightestimationmachinelearningmodelsforurbanimageanalysis AT rubenmartinezmarin automaticbuildingheightestimationmachinelearningmodelsforurbanimageanalysis AT beatrizgonzalezrodrigo automaticbuildingheightestimationmachinelearningmodelsforurbanimageanalysis AT miguelmarchamalosacristan automaticbuildingheightestimationmachinelearningmodelsforurbanimageanalysis |