Privacy protection in street-view panoramas using depth and multi-view imagery

Ries Uittenbogaard, Clint Sebastian, J.A. Vijverberg, Bas Boom, Dariu Gavrila, Peter de With

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademic

4 Citaten (Scopus)
23 Downloads (Pure)

Samenvatting

The current paradigm in privacy protection in street-view images is to detect and blur sensitive information. In this paper, we propose a framework that is an alternative to blurring, which automatically removes and inpaints moving objects (e.g. pedestrians, vehicles) in street-view imagery. We propose a novel moving object segmentation algorithm exploiting consistencies in depth across multiple street-view images that are later combined with the results of a segmentation network. The detected moving objects are removed and inpainted with information from other views, to obtain a realistic output image such that the moving object is not visible anymore. We evaluate our results on a dataset of 1000 images to obtain a peak noise-to-signal ratio (PSNR) and L 1 loss of 27.2 dB and 2.5%, respectively. To assess overall quality, we also report the results of a survey conducted on 35 professionals, asked to visually inspect the images whether object removal and inpainting had taken place. The inpainting dataset will be made publicly available for scientific benchmarking purposes at https://research.cyclomedia.com/.

Originele taal-2Engels
Titel13th IEEE/CVF Conference on Computer Vision and Pattern Recognition, (CVPR2019)
Plaats van productiePiscataway
UitgeverijInstitute of Electrical and Electronics Engineers
Pagina's10573-10582
Aantal pagina's10
ISBN van elektronische versie978-1-7281-3293-8
DOI's
StatusGepubliceerd - jun 2019
Evenement13th IEEE/CVF Conference on Computer Vision and Pattern Recognition, (CVPR2019) - Long Beach, Verenigde Staten van Amerika
Duur: 16 jun 201920 jun 2019
http://cvpr2019.thecvf.com/

Congres

Congres13th IEEE/CVF Conference on Computer Vision and Pattern Recognition, (CVPR2019)
Verkorte titelCVPR 2019
LandVerenigde Staten van Amerika
StadLong Beach
Periode16/06/1920/06/19
Internet adres

Vingerafdruk Duik in de onderzoeksthema's van 'Privacy protection in street-view panoramas using depth and multi-view imagery'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit

    Uittenbogaard, R., Sebastian, C., Vijverberg, J. A., Boom, B., Gavrila, D., & de With, P. (2019). Privacy protection in street-view panoramas using depth and multi-view imagery. In 13th IEEE/CVF Conference on Computer Vision and Pattern Recognition, (CVPR2019) (blz. 10573-10582). [8954238] Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CVPR.2019.01083