In this work we test the power of prediction of deep learning for detection of buildings from aerial laser scanner point cloud information. Automatic extraction of built features from remote sensing data is of extreme interest for many applications. In particular latest paradigms of 3D mapping of buildings, such as CityGML and BIM, can benefit from an initial determination of building geometries. In this work we used a LiDAR dataset of urban environment from the ISPRS benchmark on urban object detection. The dataset is labelled with eight classes, two were used for this investigation: roof and facades. The objective is to test how TensorFlow neural network for deep learning can predict these two classes. Results show that for "roof" and "facades" semantic classes respectively, recall is 84% and 76% and precision is 72% and 63%. The number and distribution of correct points well represent the geometry, thus allowing to use them as support for CityGML and BIM modelling. Further tuning of the hidden layers of the DL model will likely improve results and will be tested in future investigations.

Detection of building roofs and facades from aerial laser scanning data using deep learning

PIROTTI, FRANCESCO;Zanchetta C.;Previtali M.;Della Torre S.
2019-01-01

Abstract

In this work we test the power of prediction of deep learning for detection of buildings from aerial laser scanner point cloud information. Automatic extraction of built features from remote sensing data is of extreme interest for many applications. In particular latest paradigms of 3D mapping of buildings, such as CityGML and BIM, can benefit from an initial determination of building geometries. In this work we used a LiDAR dataset of urban environment from the ISPRS benchmark on urban object detection. The dataset is labelled with eight classes, two were used for this investigation: roof and facades. The objective is to test how TensorFlow neural network for deep learning can predict these two classes. Results show that for "roof" and "facades" semantic classes respectively, recall is 84% and 76% and precision is 72% and 63%. The number and distribution of correct points well represent the geometry, thus allowing to use them as support for CityGML and BIM modelling. Further tuning of the hidden layers of the DL model will likely improve results and will be tested in future investigations.
2019
2ND INTERNATIONAL CONFERENCE OF GEOMATICS AND RESTORATION (GEORES 2019)
Deep learning; Laser scanning; Lidar; Semantic classification; Tensorflow
File in questo prodotto:
File Dimensione Formato  
isprs-archives-XLII-2-W11-975-2019.pdf

accesso aperto

Dimensione 1.21 MB
Formato Adobe PDF
1.21 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1090187
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 16
  • ???jsp.display-item.citation.isi??? 10
social impact