The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Une composition d'image simple basée sur la profondeur est proposée, qui utilise deux images fixes avec des informations sur la profondeur, un objet d'arrière-plan et un objet de premier plan. La méthode proposée peut placer l'objet à différents endroits en arrière-plan en tenant compte de la profondeur dans le système de coordonnées du monde 3D. La principale caractéristique est qu'un algorithme simple est fourni, qui nous permet de réaliser un mouvement vers la profondeur dans le plan de la caméra, sans avoir conscience du système de coordonnées du monde 3D. Deux algorithmes sont proposés (P-OMDD et O-OMDD), basés sur le modèle de caméra sténopé. Comme avantage, l’étalonnage de la caméra n’est pas requis avant d’appliquer l’algorithme dans ces méthodes. Puisqu’une seule image est utilisée pour la représentation de l’objet, chacune des méthodes proposées a ses limites en termes de fidélité de l’image composite. P-OMDD reproduit fidèlement l'angle sous lequel l'objet est vu, mais les pixels de la surface cachée sont manquants. Au contraire, O-OMDD peut éviter le problème de la surface cachée, mais l'angle de l'objet est fixe, partout où il se déplace. Il a été vérifié à travers plusieurs expériences qu'en utilisant O-OMDD, des images composites subjectivement naturelles peuvent être obtenues sous n'importe quel mouvement d'objet, en termes de taille et de position dans le plan de la caméra. Les tâches futures incluent l'amélioration du changement d'éclairage dû aux changements de position et à la perte partielle d'objets due au bruit dans les images en profondeur.
Mami NAGOYA
Kanagawa Institute of Technology
Tomoaki KIMURA
Kanagawa Institute of Technology
Hiroyuki TSUJI
Kanagawa Institute of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Mami NAGOYA, Tomoaki KIMURA, Hiroyuki TSUJI, "A Simple Depth-Key-Based Image Composition Considering Object Movement in Depth Direction" in IEICE TRANSACTIONS on Fundamentals,
vol. E103-A, no. 12, pp. 1603-1608, December 2020, doi: 10.1587/transfun.2020SML0005.
Abstract: A simple depth-key-based image composition is proposed, which uses two still images with depth information, background and foreground object. The proposed method can place the object at various locations in the background considering the depth in the 3D world coordinate system. The main feature is that a simple algorithm is provided, which enables us to achieve the depthward movement within the camera plane, without being aware of the 3D world coordinate system. Two algorithms are proposed (P-OMDD and O-OMDD), which are based on the pin-hole camera model. As an advantage, camera calibration is not required before applying the algorithm in these methods. Since a single image is used for the object representation, each of the proposed methods has its limitations in terms of fidelity of the composite image. P-OMDD faithfully reproduces the angle at which the object is seen, but the pixels of the hidden surface are missing. On the contrary, O-OMDD can avoid the hidden surface problem, but the angle of the object is fixed, wherever it moves. It is verified through several experiments that, when using O-OMDD, subjectively natural composite images can be obtained under any object movement, in terms of size and position in the camera plane. Future tasks include improving the change in illumination due to positional changes and the partial loss of objects due to noise in depth images.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2020SML0005/_p
Copier
@ARTICLE{e103-a_12_1603,
author={Mami NAGOYA, Tomoaki KIMURA, Hiroyuki TSUJI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Simple Depth-Key-Based Image Composition Considering Object Movement in Depth Direction},
year={2020},
volume={E103-A},
number={12},
pages={1603-1608},
abstract={A simple depth-key-based image composition is proposed, which uses two still images with depth information, background and foreground object. The proposed method can place the object at various locations in the background considering the depth in the 3D world coordinate system. The main feature is that a simple algorithm is provided, which enables us to achieve the depthward movement within the camera plane, without being aware of the 3D world coordinate system. Two algorithms are proposed (P-OMDD and O-OMDD), which are based on the pin-hole camera model. As an advantage, camera calibration is not required before applying the algorithm in these methods. Since a single image is used for the object representation, each of the proposed methods has its limitations in terms of fidelity of the composite image. P-OMDD faithfully reproduces the angle at which the object is seen, but the pixels of the hidden surface are missing. On the contrary, O-OMDD can avoid the hidden surface problem, but the angle of the object is fixed, wherever it moves. It is verified through several experiments that, when using O-OMDD, subjectively natural composite images can be obtained under any object movement, in terms of size and position in the camera plane. Future tasks include improving the change in illumination due to positional changes and the partial loss of objects due to noise in depth images.},
keywords={},
doi={10.1587/transfun.2020SML0005},
ISSN={1745-1337},
month={December},}
Copier
TY - JOUR
TI - A Simple Depth-Key-Based Image Composition Considering Object Movement in Depth Direction
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1603
EP - 1608
AU - Mami NAGOYA
AU - Tomoaki KIMURA
AU - Hiroyuki TSUJI
PY - 2020
DO - 10.1587/transfun.2020SML0005
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E103-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2020
AB - A simple depth-key-based image composition is proposed, which uses two still images with depth information, background and foreground object. The proposed method can place the object at various locations in the background considering the depth in the 3D world coordinate system. The main feature is that a simple algorithm is provided, which enables us to achieve the depthward movement within the camera plane, without being aware of the 3D world coordinate system. Two algorithms are proposed (P-OMDD and O-OMDD), which are based on the pin-hole camera model. As an advantage, camera calibration is not required before applying the algorithm in these methods. Since a single image is used for the object representation, each of the proposed methods has its limitations in terms of fidelity of the composite image. P-OMDD faithfully reproduces the angle at which the object is seen, but the pixels of the hidden surface are missing. On the contrary, O-OMDD can avoid the hidden surface problem, but the angle of the object is fixed, wherever it moves. It is verified through several experiments that, when using O-OMDD, subjectively natural composite images can be obtained under any object movement, in terms of size and position in the camera plane. Future tasks include improving the change in illumination due to positional changes and the partial loss of objects due to noise in depth images.
ER -