Super-resolved 3D reconstruction for parking assistance using projective transformation

Keiko Nakajima, Takenao Ohkawa, Shiho Tanaka, Toshio Ito

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

Abstract

Recently, computer vision technology has been widely adopted for the safety technology of automobiles. In conventional methods, research on the recognition of obstacles of similar height has advanced, such as the recognition of pedestrians or nearby vehicles. However, we must also help drivers recognize the height of obstacles that the vehicles cannot drive over, such as parking lot sprags and curbstones. We propose a 3D reconstruction method of small obstacles in this paper. Due to the cost and the problem of camera calibration, we use an in-vehicle monocular camera. Generally, a camera-view image is used for 3D reconstruction. For the camera-view image, objects far from the camera are reflected as small and their reconstructed 3D information has less accuracy due to the mismatch that occurs in the template matching process. Therefore, we propose a correct matching method using the shape of the tops of the same object because it does not change the sequential top-view images. Using our proposed method, more correct 3D information can be acquired than with camera-view image.

Original languageEnglish
Title of host publicationFCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision
Pages300-304
Number of pages5
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event19th Korea-Japan Joint Workshop on Frontiers of Computer Vision, FCV 2013 - Incheon
Duration: 2013 Jan 302013 Feb 1

Other

Other19th Korea-Japan Joint Workshop on Frontiers of Computer Vision, FCV 2013
CityIncheon
Period13/1/3013/2/1

Fingerprint

Parking
Cameras
Template matching
Computer vision
Automobiles
Calibration
Costs

Keywords

  • 3D reconstruction
  • ITS
  • Monocular camera
  • Perspective transformation

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Nakajima, K., Ohkawa, T., Tanaka, S., & Ito, T. (2013). Super-resolved 3D reconstruction for parking assistance using projective transformation. In FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision (pp. 300-304). [6485509] https://doi.org/10.1109/FCV.2013.6485509

Super-resolved 3D reconstruction for parking assistance using projective transformation. / Nakajima, Keiko; Ohkawa, Takenao; Tanaka, Shiho; Ito, Toshio.

FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision. 2013. p. 300-304 6485509.

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

Nakajima, K, Ohkawa, T, Tanaka, S & Ito, T 2013, Super-resolved 3D reconstruction for parking assistance using projective transformation. in FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision., 6485509, pp. 300-304, 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision, FCV 2013, Incheon, 13/1/30. https://doi.org/10.1109/FCV.2013.6485509
Nakajima K, Ohkawa T, Tanaka S, Ito T. Super-resolved 3D reconstruction for parking assistance using projective transformation. In FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision. 2013. p. 300-304. 6485509 https://doi.org/10.1109/FCV.2013.6485509
Nakajima, Keiko ; Ohkawa, Takenao ; Tanaka, Shiho ; Ito, Toshio. / Super-resolved 3D reconstruction for parking assistance using projective transformation. FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision. 2013. pp. 300-304
@inproceedings{8e1a5a61d859403e85cbaffe1e92599e,
title = "Super-resolved 3D reconstruction for parking assistance using projective transformation",
abstract = "Recently, computer vision technology has been widely adopted for the safety technology of automobiles. In conventional methods, research on the recognition of obstacles of similar height has advanced, such as the recognition of pedestrians or nearby vehicles. However, we must also help drivers recognize the height of obstacles that the vehicles cannot drive over, such as parking lot sprags and curbstones. We propose a 3D reconstruction method of small obstacles in this paper. Due to the cost and the problem of camera calibration, we use an in-vehicle monocular camera. Generally, a camera-view image is used for 3D reconstruction. For the camera-view image, objects far from the camera are reflected as small and their reconstructed 3D information has less accuracy due to the mismatch that occurs in the template matching process. Therefore, we propose a correct matching method using the shape of the tops of the same object because it does not change the sequential top-view images. Using our proposed method, more correct 3D information can be acquired than with camera-view image.",
keywords = "3D reconstruction, ITS, Monocular camera, Perspective transformation",
author = "Keiko Nakajima and Takenao Ohkawa and Shiho Tanaka and Toshio Ito",
year = "2013",
doi = "10.1109/FCV.2013.6485509",
language = "English",
isbn = "9781467356206",
pages = "300--304",
booktitle = "FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision",

}

TY - GEN

T1 - Super-resolved 3D reconstruction for parking assistance using projective transformation

AU - Nakajima, Keiko

AU - Ohkawa, Takenao

AU - Tanaka, Shiho

AU - Ito, Toshio

PY - 2013

Y1 - 2013

N2 - Recently, computer vision technology has been widely adopted for the safety technology of automobiles. In conventional methods, research on the recognition of obstacles of similar height has advanced, such as the recognition of pedestrians or nearby vehicles. However, we must also help drivers recognize the height of obstacles that the vehicles cannot drive over, such as parking lot sprags and curbstones. We propose a 3D reconstruction method of small obstacles in this paper. Due to the cost and the problem of camera calibration, we use an in-vehicle monocular camera. Generally, a camera-view image is used for 3D reconstruction. For the camera-view image, objects far from the camera are reflected as small and their reconstructed 3D information has less accuracy due to the mismatch that occurs in the template matching process. Therefore, we propose a correct matching method using the shape of the tops of the same object because it does not change the sequential top-view images. Using our proposed method, more correct 3D information can be acquired than with camera-view image.

AB - Recently, computer vision technology has been widely adopted for the safety technology of automobiles. In conventional methods, research on the recognition of obstacles of similar height has advanced, such as the recognition of pedestrians or nearby vehicles. However, we must also help drivers recognize the height of obstacles that the vehicles cannot drive over, such as parking lot sprags and curbstones. We propose a 3D reconstruction method of small obstacles in this paper. Due to the cost and the problem of camera calibration, we use an in-vehicle monocular camera. Generally, a camera-view image is used for 3D reconstruction. For the camera-view image, objects far from the camera are reflected as small and their reconstructed 3D information has less accuracy due to the mismatch that occurs in the template matching process. Therefore, we propose a correct matching method using the shape of the tops of the same object because it does not change the sequential top-view images. Using our proposed method, more correct 3D information can be acquired than with camera-view image.

KW - 3D reconstruction

KW - ITS

KW - Monocular camera

KW - Perspective transformation

UR - http://www.scopus.com/inward/record.url?scp=84875996316&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875996316&partnerID=8YFLogxK

U2 - 10.1109/FCV.2013.6485509

DO - 10.1109/FCV.2013.6485509

M3 - Conference contribution

AN - SCOPUS:84875996316

SN - 9781467356206

SP - 300

EP - 304

BT - FCV 2013 - Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision

ER -