Unsupervised TOF image segmentation through spectral clustering and region merging

Título:

Unsupervised TOF image segmentation through spectral clustering and region merging

Autor:

Lorenti, Luciano

Colaboradores:

; Giacomantone, Javier Oscar; Bria, Oscar Norberto

Temas:

IMÁGENES

En:

Journal of Computer Science & Technology, 18(2), pp. 97-104.

Resumen:

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.

URL/DOI:

https://doi.org/10.24215/16666038.18.e11

Palabras clave:

segmentación de imágenesagrupamiento espectral

Medio:

Soporte electrónico

Tipo de documento:

Artículo

Descripción física:

1 archivo (857,2 kB)

Idioma:

Inglés

Publicación:

, 2018

Puede solicitar más fácilmente el ejemplar con: A1202

Ver estantes