Vehicle lateral position estimation method based on matching of top-view images

Tomoaki Teshima, Hideo Saito, Shinji Ozawa, Keiichi Yamamoto, Toru Ihara

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

7 Citations (Scopus)

Abstract

In this paper, a method to estimate the lateral position of the vehicle from a sequence of moving camera images is proposed. Proposed method relies on the plane projective transform (Homography) between the ground and the image plane of the present and the next frame. Homographies are obtained according to the information of the calibrated camera and the vehicles' speed. The movement of the camera is obtained by the registration of the 2 consecutive input images. The proposed method does not rely on extraction of features such as lines, flow vectors or lane markers, but based on matching of warped top-view images between two consecutive frames. Therefore, vehicle movement can be estimated even from images without such explicit image features or without special sensors or GPS. In this paper, experiments are done with both synthesized and real images and enough accuracy is shown even compared to conventional method.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages626-629
Number of pages4
Volume4
DOIs
Publication statusPublished - 2006
Event18th International Conference on Pattern Recognition, ICPR 2006 - Hong Kong, China
Duration: 2006 Aug 202006 Aug 24

Other

Other18th International Conference on Pattern Recognition, ICPR 2006
CountryChina
CityHong Kong
Period06/8/2006/8/24

Fingerprint

Cameras
Global positioning system
Sensors
Experiments

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Cite this

Teshima, T., Saito, H., Ozawa, S., Yamamoto, K., & Ihara, T. (2006). Vehicle lateral position estimation method based on matching of top-view images. In Proceedings - International Conference on Pattern Recognition (Vol. 4, pp. 626-629). [1699919] https://doi.org/10.1109/ICPR.2006.1166

Vehicle lateral position estimation method based on matching of top-view images. / Teshima, Tomoaki; Saito, Hideo; Ozawa, Shinji; Yamamoto, Keiichi; Ihara, Toru.

Proceedings - International Conference on Pattern Recognition. Vol. 4 2006. p. 626-629 1699919.

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

Teshima, T, Saito, H, Ozawa, S, Yamamoto, K & Ihara, T 2006, Vehicle lateral position estimation method based on matching of top-view images. in Proceedings - International Conference on Pattern Recognition. vol. 4, 1699919, pp. 626-629, 18th International Conference on Pattern Recognition, ICPR 2006, Hong Kong, China, 06/8/20. https://doi.org/10.1109/ICPR.2006.1166
Teshima T, Saito H, Ozawa S, Yamamoto K, Ihara T. Vehicle lateral position estimation method based on matching of top-view images. In Proceedings - International Conference on Pattern Recognition. Vol. 4. 2006. p. 626-629. 1699919 https://doi.org/10.1109/ICPR.2006.1166
Teshima, Tomoaki ; Saito, Hideo ; Ozawa, Shinji ; Yamamoto, Keiichi ; Ihara, Toru. / Vehicle lateral position estimation method based on matching of top-view images. Proceedings - International Conference on Pattern Recognition. Vol. 4 2006. pp. 626-629
@inproceedings{646480b19b1c442b8fe857076eb5b7da,
title = "Vehicle lateral position estimation method based on matching of top-view images",
abstract = "In this paper, a method to estimate the lateral position of the vehicle from a sequence of moving camera images is proposed. Proposed method relies on the plane projective transform (Homography) between the ground and the image plane of the present and the next frame. Homographies are obtained according to the information of the calibrated camera and the vehicles' speed. The movement of the camera is obtained by the registration of the 2 consecutive input images. The proposed method does not rely on extraction of features such as lines, flow vectors or lane markers, but based on matching of warped top-view images between two consecutive frames. Therefore, vehicle movement can be estimated even from images without such explicit image features or without special sensors or GPS. In this paper, experiments are done with both synthesized and real images and enough accuracy is shown even compared to conventional method.",
author = "Tomoaki Teshima and Hideo Saito and Shinji Ozawa and Keiichi Yamamoto and Toru Ihara",
year = "2006",
doi = "10.1109/ICPR.2006.1166",
language = "English",
volume = "4",
pages = "626--629",
booktitle = "Proceedings - International Conference on Pattern Recognition",

}

TY - GEN

T1 - Vehicle lateral position estimation method based on matching of top-view images

AU - Teshima, Tomoaki

AU - Saito, Hideo

AU - Ozawa, Shinji

AU - Yamamoto, Keiichi

AU - Ihara, Toru

PY - 2006

Y1 - 2006

N2 - In this paper, a method to estimate the lateral position of the vehicle from a sequence of moving camera images is proposed. Proposed method relies on the plane projective transform (Homography) between the ground and the image plane of the present and the next frame. Homographies are obtained according to the information of the calibrated camera and the vehicles' speed. The movement of the camera is obtained by the registration of the 2 consecutive input images. The proposed method does not rely on extraction of features such as lines, flow vectors or lane markers, but based on matching of warped top-view images between two consecutive frames. Therefore, vehicle movement can be estimated even from images without such explicit image features or without special sensors or GPS. In this paper, experiments are done with both synthesized and real images and enough accuracy is shown even compared to conventional method.

AB - In this paper, a method to estimate the lateral position of the vehicle from a sequence of moving camera images is proposed. Proposed method relies on the plane projective transform (Homography) between the ground and the image plane of the present and the next frame. Homographies are obtained according to the information of the calibrated camera and the vehicles' speed. The movement of the camera is obtained by the registration of the 2 consecutive input images. The proposed method does not rely on extraction of features such as lines, flow vectors or lane markers, but based on matching of warped top-view images between two consecutive frames. Therefore, vehicle movement can be estimated even from images without such explicit image features or without special sensors or GPS. In this paper, experiments are done with both synthesized and real images and enough accuracy is shown even compared to conventional method.

UR - http://www.scopus.com/inward/record.url?scp=34147162802&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34147162802&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2006.1166

DO - 10.1109/ICPR.2006.1166

M3 - Conference contribution

AN - SCOPUS:34147162802

VL - 4

SP - 626

EP - 629

BT - Proceedings - International Conference on Pattern Recognition

ER -