Image processing pipeline for segmentation and material classification based on multispectral high dynamic range polarimetric images
Metadatos
Mostrar el registro completo del ítemAutor
Martínez Domingo, Miguel Ángel; Valero Benito, Eva María; Hernández Andrés, Javier; Tominaga, Shoji; Horiuchi, Takahiko; Hirai, KeitaEditorial
Optica
Materia
Spectral imaging Segmentation Classification
Fecha
2017-11-16Referencia bibliográfica
Martínez-Domingo, M. Á., Valero, E. M., Hernández-Andrés, J., Tominaga, S., Horiuchi, T., & Hirai, K. (2017). Image processing pipeline for segmentation and material classification based on multispectral high dynamic range polarimetric images. Optics express, 25(24), 30073-30090.
Patrocinador
Spanish Secretary of State of Research, Development and Innovation (SEIDI), within the Ministry of Economy and Competitiveness (DPI2015-64571-R).Resumen
We propose a method for the capture of high dynamic range (HDR), multispectral
(MS), polarimetric (Pol) images of indoor scenes using a liquid crystal tunable filter (LCTF). We
have included the adaptive exposure estimation (AEE) method to fully automatize the capturing
process. We also propose a pre-processing method which can be applied for the registration of
HDR images after they are already built as the result of combining di erent low dynamic range
(LDR) images. This method is applied to ensure a correct alignment of the di erent polarization
HDR images for each spectral band. We have focused our e orts in two main applications:
object segmentation and classification into metal and dielectric classes. We have simplified the
segmentation using mean shift combined with cluster averaging and region merging techniques.
We compare the performance of our segmentation with that of Ncut and Watershed methods. For
the classification task, we propose to use information not only in the highlight regions but also in
their surrounding area, extracted from the degree of linear polarization (DoLP) maps. We present
experimental results which proof that the proposed image processing pipeline outperforms
previous techniques developed specifically for MSHDRPol image cubes.