Unsupervised TOF Image Segmentation through Spectral Clustering and Region Merging
Journal of Computer Science and Technology · 2018
DOI: 10.24215/16666038.18.e11 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computer Science and Technology, 2018. Verfasst von Luciano Lorenti und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Time of Flight (TOF) cameras generate two simultaneous images, one of intensity and one of range. This allows to tackle segmentation problems in which the separate use of intensity or range information is not enough to extract objects of interest from the 3D scene. In turn, range information allows to obtain a normal vector estimation of each point of the captured surfaces. This article presents a semi-supervised spectral clustering method which combines intensity and range information as well as normal vector orientations to improve segmentation results. The main contribution of this article consists in the use of a statistical region merging as a final step of the segmentation method. The region merging process combines adjacent regions which satisfy a similarity criterion. The performance of the proposed method was evaluated over real images. The use of this final step presents preliminary improvements in the metrics evaluated.
Zitieren
APA
Lorenti, L., Giacomantone, J., & Bria, O. (2018). Unsupervised TOF Image Segmentation through Spectral Clustering and Region Merging. Journal of Computer Science and Technology. https://doi.org/10.24215/16666038.18.e11
Vancouver
Lorenti L, Giacomantone J, Bria O. Unsupervised TOF Image Segmentation through Spectral Clustering and Region Merging. Journal of Computer Science and Technology. 2018. doi:10.24215/16666038.18.e11
BibTeX
@article{Lorenti2018,
author = {Lorenti, Luciano and Giacomantone, Javier and Bria, Oscar},
title = {Unsupervised TOF Image Segmentation through Spectral Clustering and Region Merging},
journal = {Journal of Computer Science and Technology},
year = {2018},
doi = {10.24215/16666038.18.e11}
}
EUVIMED