Camera position estimation method based on matching of Top-View images for running vehicle

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

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

Abstract

In this paper, a method which estimates the trajectory of the vehicle from a single vehicle camera is proposed. The proposed method is a model based method which assumes that the vehicle is running on a planar road. The input image is converted to a Top- View image and a matching (registration) between the next Top- View image is done. The registration is done based on an assumed velocity parameter, and repeated with entire candidate parameters. In this paper, a simple model and the particle filter is introduced to decrease the computation cost. Simple model gives a constraint to the registration of the Top-View images, and the particle filter decreases the number of the candidate parameters. Position of the camera is obtained by accumulating the velocity parameters. Experiments shows 3 results. Enough decreasement of the computation cost, suitable estimated trajectory and small enough computation cost to estimate the trajectory of the vehicle.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume6496
DOIs
Publication statusPublished - 2007
EventReal-Time Image Processing 2007 - San Jose, CA, United States
Duration: 2007 Jan 292007 Jan 30

Other

OtherReal-Time Image Processing 2007
CountryUnited States
CitySan Jose, CA
Period07/1/2907/1/30

Fingerprint

vehicles
Cameras
cameras
Trajectories
trajectories
costs
filters
Costs
estimates
roads
Experiments

Keywords

  • Homography
  • ITS
  • Vehicle camera
  • Vehicle position estimation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Teshima, T., Saito, H., Ozawa, S., Yamamoto, K., & Ihara, T. (2007). Camera position estimation method based on matching of Top-View images for running vehicle. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 6496). [649605] https://doi.org/10.1117/12.704067

Camera position estimation method based on matching of Top-View images for running vehicle. / Teshima, Tomoaki; Saito, Hideo; Ozawa, Shinji; Yamamoto, Keiichi; Ihara, Toru.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6496 2007. 649605.

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

Teshima, T, Saito, H, Ozawa, S, Yamamoto, K & Ihara, T 2007, Camera position estimation method based on matching of Top-View images for running vehicle. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 6496, 649605, Real-Time Image Processing 2007, San Jose, CA, United States, 07/1/29. https://doi.org/10.1117/12.704067
Teshima T, Saito H, Ozawa S, Yamamoto K, Ihara T. Camera position estimation method based on matching of Top-View images for running vehicle. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6496. 2007. 649605 https://doi.org/10.1117/12.704067
Teshima, Tomoaki ; Saito, Hideo ; Ozawa, Shinji ; Yamamoto, Keiichi ; Ihara, Toru. / Camera position estimation method based on matching of Top-View images for running vehicle. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6496 2007.
@inproceedings{b106918a355740d7b2bbfff43f2a3105,
title = "Camera position estimation method based on matching of Top-View images for running vehicle",
abstract = "In this paper, a method which estimates the trajectory of the vehicle from a single vehicle camera is proposed. The proposed method is a model based method which assumes that the vehicle is running on a planar road. The input image is converted to a Top- View image and a matching (registration) between the next Top- View image is done. The registration is done based on an assumed velocity parameter, and repeated with entire candidate parameters. In this paper, a simple model and the particle filter is introduced to decrease the computation cost. Simple model gives a constraint to the registration of the Top-View images, and the particle filter decreases the number of the candidate parameters. Position of the camera is obtained by accumulating the velocity parameters. Experiments shows 3 results. Enough decreasement of the computation cost, suitable estimated trajectory and small enough computation cost to estimate the trajectory of the vehicle.",
keywords = "Homography, ITS, Vehicle camera, Vehicle position estimation",
author = "Tomoaki Teshima and Hideo Saito and Shinji Ozawa and Keiichi Yamamoto and Toru Ihara",
year = "2007",
doi = "10.1117/12.704067",
language = "English",
isbn = "0819466093",
volume = "6496",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Camera position estimation method based on matching of Top-View images for running vehicle

AU - Teshima, Tomoaki

AU - Saito, Hideo

AU - Ozawa, Shinji

AU - Yamamoto, Keiichi

AU - Ihara, Toru

PY - 2007

Y1 - 2007

N2 - In this paper, a method which estimates the trajectory of the vehicle from a single vehicle camera is proposed. The proposed method is a model based method which assumes that the vehicle is running on a planar road. The input image is converted to a Top- View image and a matching (registration) between the next Top- View image is done. The registration is done based on an assumed velocity parameter, and repeated with entire candidate parameters. In this paper, a simple model and the particle filter is introduced to decrease the computation cost. Simple model gives a constraint to the registration of the Top-View images, and the particle filter decreases the number of the candidate parameters. Position of the camera is obtained by accumulating the velocity parameters. Experiments shows 3 results. Enough decreasement of the computation cost, suitable estimated trajectory and small enough computation cost to estimate the trajectory of the vehicle.

AB - In this paper, a method which estimates the trajectory of the vehicle from a single vehicle camera is proposed. The proposed method is a model based method which assumes that the vehicle is running on a planar road. The input image is converted to a Top- View image and a matching (registration) between the next Top- View image is done. The registration is done based on an assumed velocity parameter, and repeated with entire candidate parameters. In this paper, a simple model and the particle filter is introduced to decrease the computation cost. Simple model gives a constraint to the registration of the Top-View images, and the particle filter decreases the number of the candidate parameters. Position of the camera is obtained by accumulating the velocity parameters. Experiments shows 3 results. Enough decreasement of the computation cost, suitable estimated trajectory and small enough computation cost to estimate the trajectory of the vehicle.

KW - Homography

KW - ITS

KW - Vehicle camera

KW - Vehicle position estimation

UR - http://www.scopus.com/inward/record.url?scp=34548200781&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548200781&partnerID=8YFLogxK

U2 - 10.1117/12.704067

DO - 10.1117/12.704067

M3 - Conference contribution

AN - SCOPUS:34548200781

SN - 0819466093

SN - 9780819466099

VL - 6496

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -