Bootstrapped CNNS for building segmentation on RGB-D aerial imagery

C. Sebastian, B. Boom, T. van Lankveld, E. Bondarev, P.H.N. de With

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

1 Citaat (Scopus)
67 Downloads (Pure)

Samenvatting

Detection of buildings and other objects from aerial images has various applications in urban planning and map making. Automated building detection from aerial imagery is a challenging task, as it is prone to varying lighting conditions, shadows and occlusions. Convolutional Neural Networks (CNNs) are robust against some of these variations, although they fail to distinguish easy and difficult examples. We train a detection algorithm from RGB-D images to obtain a segmented mask by using the CNN architecture DenseNet. First, we improve the performance of the model by applying a statistical re-sampling technique called Bootstrapping and demonstrate that more informative examples are retained. Second, the proposed method outperforms the non-bootstrapped version by utilizing only one-sixth of the original training data and it obtains a precision-recall break-even of 95.10 % on our aerial imagery dataset.

Originele taal-2Engels
TitelISPRS TC IV Mid-term Symposium “3D Spatial Information Science – The Engine of Change”
RedacteurenS. Zlatanova, S. Dragicevic, G. Sithole
UitgeverijInternational Society of Photogrammetry and Remote Sensing (ISPRS)
Pagina's187-192
Aantal pagina's6
DOI's
StatusGepubliceerd - 19 sep 2018
Evenement2018 ISPRS TC IV Mid-Term Symposium on 3D Spatial Information Science - The Engine of Change - Delft, Nederland
Duur: 1 okt 20185 okt 2018

Publicatie series

NaamISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Nummer4
Volume4
ISSN van geprinte versie2194-9042

Congres

Congres2018 ISPRS TC IV Mid-Term Symposium on 3D Spatial Information Science - The Engine of Change
LandNederland
StadDelft
Periode1/10/185/10/18

Vingerafdruk Duik in de onderzoeksthema's van 'Bootstrapped CNNS for building segmentation on RGB-D aerial imagery'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit

    Sebastian, C., Boom, B., van Lankveld, T., Bondarev, E., & de With, P. H. N. (2018). Bootstrapped CNNS for building segmentation on RGB-D aerial imagery. In S. Zlatanova, S. Dragicevic, & G. Sithole (editors), ISPRS TC IV Mid-term Symposium “3D Spatial Information Science – The Engine of Change” (blz. 187-192). (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences; Vol. 4, Nr. 4). International Society of Photogrammetry and Remote Sensing (ISPRS). https://doi.org/10.5194/isprs-annals-IV-4-187-2018