Privacy protection in street-view panoramas using depth and multi-view imagery
| Autor: | Ries Uittenbogaard, Clint Sebastian, Julien Vijverberg, Bas Boom, Dariu M. Gavrila, Peter H.N. de With |
|---|---|
| Přispěvatelé: | Video Coding & Architectures |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
moving object segmentation Computer science Computer Vision and Pattern Recognition (cs.CV) privacy protection inpainting Computer Science - Computer Vision and Pattern Recognition Inpainting ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology 010501 environmental sciences 01 natural sciences Image (mathematics) 0202 electrical engineering electronic engineering information engineering Segmentation Computer vision 0105 earth and related environmental sciences business.industry Privacy protection Object (computer science) Vision Applications and Systems GAN Others 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | 13th IEEE/CVF Conference on Computer Vision and Pattern Recognition, (CVPR2019), 10573-10582 STARTPAGE=10573;ENDPAGE=10582;TITLE=13th IEEE/CVF Conference on Computer Vision and Pattern Recognition, (CVPR2019) Proceedings IEEE Computer Vision and Pattern Recognition (CVPR 2019) CVPR |
| Popis: | 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 L1 loss of 27.2 dB and 2.5%, respectively. To ensure the subjective quality, 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 Comment: Accepted to CVPR 2019. Dataset (and provided link) will be made available before the CVPR |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|