New method to detect object and estimate the position and the orientation from an image using a 3-D model having feature points

Masashi Kayanuma, Masafumi Hagiwara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a new approach to detect a three-dimensional (3-D) object and to estimate its position and orientation. The proposed system can estimate the object's 3-D pose from a single input image by using 3-D model with feature points. The 3-D model is employed in order to represent 3-D object, and the system can create 2-D models projected from various viewpoints. Then, the system compares each 2-D model with the input image and calculates the matching rate, taking notice of some partial features of the object. This object recognition can be regarded as an optimization, problem: a maximum search problem of the model's matching rate. In the proposed system, a genetic algorithm (GA) is employed for this optimization. In the computer experiments, we took up a car as an example of the object. We have tested various kinds of images and obtained excellent results.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
PublisherIEEE
Volume4
Publication statusPublished - 1999
Event1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics' - Tokyo, Jpn
Duration: 1999 Oct 121999 Oct 15

Other

Other1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics'
CityTokyo, Jpn
Period99/10/1299/10/15

Fingerprint

Object recognition
Railroad cars
Genetic algorithms
Experiments

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Kayanuma, M., & Hagiwara, M. (1999). New method to detect object and estimate the position and the orientation from an image using a 3-D model having feature points. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 4). IEEE.

New method to detect object and estimate the position and the orientation from an image using a 3-D model having feature points. / Kayanuma, Masashi; Hagiwara, Masafumi.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 4 IEEE, 1999.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kayanuma, M & Hagiwara, M 1999, New method to detect object and estimate the position and the orientation from an image using a 3-D model having feature points. in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. vol. 4, IEEE, 1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics', Tokyo, Jpn, 99/10/12.
Kayanuma M, Hagiwara M. New method to detect object and estimate the position and the orientation from an image using a 3-D model having feature points. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 4. IEEE. 1999
Kayanuma, Masashi ; Hagiwara, Masafumi. / New method to detect object and estimate the position and the orientation from an image using a 3-D model having feature points. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 4 IEEE, 1999.
@inproceedings{f8617d19b5f847e4a8757d9c38fe4495,
title = "New method to detect object and estimate the position and the orientation from an image using a 3-D model having feature points",
abstract = "In this paper, we propose a new approach to detect a three-dimensional (3-D) object and to estimate its position and orientation. The proposed system can estimate the object's 3-D pose from a single input image by using 3-D model with feature points. The 3-D model is employed in order to represent 3-D object, and the system can create 2-D models projected from various viewpoints. Then, the system compares each 2-D model with the input image and calculates the matching rate, taking notice of some partial features of the object. This object recognition can be regarded as an optimization, problem: a maximum search problem of the model's matching rate. In the proposed system, a genetic algorithm (GA) is employed for this optimization. In the computer experiments, we took up a car as an example of the object. We have tested various kinds of images and obtained excellent results.",
author = "Masashi Kayanuma and Masafumi Hagiwara",
year = "1999",
language = "English",
volume = "4",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
publisher = "IEEE",

}

TY - GEN

T1 - New method to detect object and estimate the position and the orientation from an image using a 3-D model having feature points

AU - Kayanuma, Masashi

AU - Hagiwara, Masafumi

PY - 1999

Y1 - 1999

N2 - In this paper, we propose a new approach to detect a three-dimensional (3-D) object and to estimate its position and orientation. The proposed system can estimate the object's 3-D pose from a single input image by using 3-D model with feature points. The 3-D model is employed in order to represent 3-D object, and the system can create 2-D models projected from various viewpoints. Then, the system compares each 2-D model with the input image and calculates the matching rate, taking notice of some partial features of the object. This object recognition can be regarded as an optimization, problem: a maximum search problem of the model's matching rate. In the proposed system, a genetic algorithm (GA) is employed for this optimization. In the computer experiments, we took up a car as an example of the object. We have tested various kinds of images and obtained excellent results.

AB - In this paper, we propose a new approach to detect a three-dimensional (3-D) object and to estimate its position and orientation. The proposed system can estimate the object's 3-D pose from a single input image by using 3-D model with feature points. The 3-D model is employed in order to represent 3-D object, and the system can create 2-D models projected from various viewpoints. Then, the system compares each 2-D model with the input image and calculates the matching rate, taking notice of some partial features of the object. This object recognition can be regarded as an optimization, problem: a maximum search problem of the model's matching rate. In the proposed system, a genetic algorithm (GA) is employed for this optimization. In the computer experiments, we took up a car as an example of the object. We have tested various kinds of images and obtained excellent results.

UR - http://www.scopus.com/inward/record.url?scp=0033351065&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033351065&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0033351065

VL - 4

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

PB - IEEE

ER -