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
Dans les méthodes conventionnelles de détection de points de fuite et de lignes de fuite, les points caractéristiques observés sont regroupés en collections qui représentent différentes lignes. Les lignes multiples sont ensuite détectées et les points de fuite sont détectés comme points d'intersection des lignes. La ligne de fuite est alors détectée en fonction des points d'intersection. Cependant, à des fins d'optimisation, ces processus doivent être intégrés et réalisés simultanément. Dans le présent article, nous supposons que le modèle de bruit observé pour les points caractéristiques est un mélange gaussien bidimensionnel et définissons la fonction de vraisemblance, y compris les points de fuite évidents et les paramètres de ligne de fuite. En conséquence, la détection simultanée décrite ci-dessus peut être formulée comme un problème d’estimation du maximum de vraisemblance. De plus, une méthode de calcul itérative pour réaliser cette estimation est proposée basée sur l'algorithme EM (Expectation Maximization). La méthode proposée implique de nouvelles techniques permettant d'obtenir une convergence stable et de réduire le coût de calcul. L'efficacité de la méthode proposée qui inclut ces techniques peut être confirmée par des simulations informatiques et des images réelles.
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
Akihiro MINAGAWA, Norio TAGAWA, Tadashi MORIYA, Toshiyuki GOTOH, "Vanishing Point and Vanishing Line Estimation with Line Clustering" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 7, pp. 1574-1582, July 2000, doi: .
Abstract: In conventional methods for detecting vanishing points and vanishing lines, the observed feature points are clustered into collections that represent different lines. The multiple lines are then detected and the vanishing points are detected as points of intersection of the lines. The vanishing line is then detected based on the points of intersection. However, for the purpose of optimization, these processes should be integrated and be achieved simultaneously. In the present paper, we assume that the observed noise model for the feature points is a two-dimensional Gaussian mixture and define the likelihood function, including obvious vanishing points and a vanishing line parameters. As a result, the above described simultaneous detection can be formulated as a maximum likelihood estimation problem. In addition, an iterative computation method for achieving this estimation is proposed based on the EM (Expectation Maximization) algorithm. The proposed method involves new techniques by which stable convergence is achieved and computational cost is reduced. The effectiveness of the proposed method that includes these techniques can be confirmed by computer simulations and real images.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_7_1574/_p
Copier
@ARTICLE{e83-d_7_1574,
author={Akihiro MINAGAWA, Norio TAGAWA, Tadashi MORIYA, Toshiyuki GOTOH, },
journal={IEICE TRANSACTIONS on Information},
title={Vanishing Point and Vanishing Line Estimation with Line Clustering},
year={2000},
volume={E83-D},
number={7},
pages={1574-1582},
abstract={In conventional methods for detecting vanishing points and vanishing lines, the observed feature points are clustered into collections that represent different lines. The multiple lines are then detected and the vanishing points are detected as points of intersection of the lines. The vanishing line is then detected based on the points of intersection. However, for the purpose of optimization, these processes should be integrated and be achieved simultaneously. In the present paper, we assume that the observed noise model for the feature points is a two-dimensional Gaussian mixture and define the likelihood function, including obvious vanishing points and a vanishing line parameters. As a result, the above described simultaneous detection can be formulated as a maximum likelihood estimation problem. In addition, an iterative computation method for achieving this estimation is proposed based on the EM (Expectation Maximization) algorithm. The proposed method involves new techniques by which stable convergence is achieved and computational cost is reduced. The effectiveness of the proposed method that includes these techniques can be confirmed by computer simulations and real images.},
keywords={},
doi={},
ISSN={},
month={July},}
Copier
TY - JOUR
TI - Vanishing Point and Vanishing Line Estimation with Line Clustering
T2 - IEICE TRANSACTIONS on Information
SP - 1574
EP - 1582
AU - Akihiro MINAGAWA
AU - Norio TAGAWA
AU - Tadashi MORIYA
AU - Toshiyuki GOTOH
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2000
AB - In conventional methods for detecting vanishing points and vanishing lines, the observed feature points are clustered into collections that represent different lines. The multiple lines are then detected and the vanishing points are detected as points of intersection of the lines. The vanishing line is then detected based on the points of intersection. However, for the purpose of optimization, these processes should be integrated and be achieved simultaneously. In the present paper, we assume that the observed noise model for the feature points is a two-dimensional Gaussian mixture and define the likelihood function, including obvious vanishing points and a vanishing line parameters. As a result, the above described simultaneous detection can be formulated as a maximum likelihood estimation problem. In addition, an iterative computation method for achieving this estimation is proposed based on the EM (Expectation Maximization) algorithm. The proposed method involves new techniques by which stable convergence is achieved and computational cost is reduced. The effectiveness of the proposed method that includes these techniques can be confirmed by computer simulations and real images.
ER -