TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

A General Framework for Depth Compression and Multi-Sensor Fusion in Asymmetric View-Plus-Depth 3D Representation

Tutkimustuotosvertaisarvioitu

Standard

A General Framework for Depth Compression and Multi-Sensor Fusion in Asymmetric View-Plus-Depth 3D Representation. / Georgiev, Mihail; Belyaev, Evgeny; Gotchev, Atanas.

julkaisussa: IEEE Access, Vuosikerta 8, 01.01.2020, s. 97516-97528.

Tutkimustuotosvertaisarvioitu

Harvard

APA

Vancouver

Author

Georgiev, Mihail ; Belyaev, Evgeny ; Gotchev, Atanas. / A General Framework for Depth Compression and Multi-Sensor Fusion in Asymmetric View-Plus-Depth 3D Representation. Julkaisussa: IEEE Access. 2020 ; Vuosikerta 8. Sivut 97516-97528.

Bibtex - Lataa

@article{308e766792d545169c80f71e5e4c5adc,
title = "A General Framework for Depth Compression and Multi-Sensor Fusion in Asymmetric View-Plus-Depth 3D Representation",
abstract = "We present a general framework which can handle different processing stages of the three-dimensional (3D) scene representation referred to as 'view-plus-depth' (V+Z). The main component of the framework is the relation between the depth map and the super-pixel segmentation of the color image. We propose a hierarchical super-pixel segmentation which keeps the same boundaries between hierarchical segmentation layers. Such segmentation allows for a corresponding depth segmentation, decimation and reconstruction with varying quality and is instrumental in tasks such as depth compression and 3D data fusion. For the latter we utilize a cross-modality reconstruction filter which is adaptive to the size of the refining super-pixel segments. We propose a novel depth encoding scheme, which includes specific arithmetic encoder and handles misalignment outliers. We demonstrate that our scheme is especially applicable for low bit-rate depth encoding and for fusing color and depth data, where the latter is noisy and with lower spatial resolution.",
keywords = "3-D depth, 3D, compression, fusion, super-pixel, time-of-flight, ToF, V+D, V+Z, view-plus-depth",
author = "Mihail Georgiev and Evgeny Belyaev and Atanas Gotchev",
note = "EXT={"}Georgiev, Mihail{"} EXT={"}Belyaev, Evgeny{"}",
year = "2020",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2020.2996689",
language = "English",
volume = "8",
pages = "97516--97528",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - A General Framework for Depth Compression and Multi-Sensor Fusion in Asymmetric View-Plus-Depth 3D Representation

AU - Georgiev, Mihail

AU - Belyaev, Evgeny

AU - Gotchev, Atanas

N1 - EXT="Georgiev, Mihail" EXT="Belyaev, Evgeny"

PY - 2020/1/1

Y1 - 2020/1/1

N2 - We present a general framework which can handle different processing stages of the three-dimensional (3D) scene representation referred to as 'view-plus-depth' (V+Z). The main component of the framework is the relation between the depth map and the super-pixel segmentation of the color image. We propose a hierarchical super-pixel segmentation which keeps the same boundaries between hierarchical segmentation layers. Such segmentation allows for a corresponding depth segmentation, decimation and reconstruction with varying quality and is instrumental in tasks such as depth compression and 3D data fusion. For the latter we utilize a cross-modality reconstruction filter which is adaptive to the size of the refining super-pixel segments. We propose a novel depth encoding scheme, which includes specific arithmetic encoder and handles misalignment outliers. We demonstrate that our scheme is especially applicable for low bit-rate depth encoding and for fusing color and depth data, where the latter is noisy and with lower spatial resolution.

AB - We present a general framework which can handle different processing stages of the three-dimensional (3D) scene representation referred to as 'view-plus-depth' (V+Z). The main component of the framework is the relation between the depth map and the super-pixel segmentation of the color image. We propose a hierarchical super-pixel segmentation which keeps the same boundaries between hierarchical segmentation layers. Such segmentation allows for a corresponding depth segmentation, decimation and reconstruction with varying quality and is instrumental in tasks such as depth compression and 3D data fusion. For the latter we utilize a cross-modality reconstruction filter which is adaptive to the size of the refining super-pixel segments. We propose a novel depth encoding scheme, which includes specific arithmetic encoder and handles misalignment outliers. We demonstrate that our scheme is especially applicable for low bit-rate depth encoding and for fusing color and depth data, where the latter is noisy and with lower spatial resolution.

KW - 3-D depth

KW - 3D

KW - compression

KW - fusion

KW - super-pixel

KW - time-of-flight

KW - ToF

KW - V+D

KW - V+Z

KW - view-plus-depth

U2 - 10.1109/ACCESS.2020.2996689

DO - 10.1109/ACCESS.2020.2996689

M3 - Article

VL - 8

SP - 97516

EP - 97528

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -