IEICE TRANSACTIONS on Information
Robust and Efficient Homography Estimation Using Directional Feature Matching of Court Points for Soccer Field Registration
Summary :
In this paper, we present an efficient and robust method for estimating Homography matrix for soccer field registration between a captured camera image and a soccer field model. The presented method first detects reliable field lines from the camera image through clustering. Constructing a novel directional feature of the intersection points of the lines in both the camera image and the model, the presented method then finds matching pairs of these points between the image and the model. Finally, Homography matrix estimations and validations are performed using the obtained matching pairs, which can reduce the required number of Homography matrix calculations. Our presented method uses possible intersection points outside image for the point matching. This effectively improves robustness and accuracy of Homography estimation as demonstrated in experimental results.
- Publication
- IEICE TRANSACTIONS on Information Vol.E104-D No.10 pp.1563-1571
- Publication Date
- 2021/10/01
- Publicized
- 2021/07/08
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2021PCP0003
- Type of Manuscript
- Special Section PAPER (Special Section on Picture Coding and Image Media Processing)
- Category
Authors
Kazuki KASAI
Chuo University
Kaoru KAWAKITA
Chuo University
Akira KUBOTA
Chuo University
Hiroki TSURUSAKI
KDDI Research, Inc.
Ryosuke WATANABE
KDDI Research, Inc.
Masaru SUGANO
KDDI Research, Inc.
Keyword
Latest Issue
Copyrights notice of machine-translated contents
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.
Cite this
Copy
Kazuki KASAI, Kaoru KAWAKITA, Akira KUBOTA, Hiroki TSURUSAKI, Ryosuke WATANABE, Masaru SUGANO, "Robust and Efficient Homography Estimation Using Directional Feature Matching of Court Points for Soccer Field Registration" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 10, pp. 1563-1571, October 2021, doi: 10.1587/transinf.2021PCP0003.
Abstract: In this paper, we present an efficient and robust method for estimating Homography matrix for soccer field registration between a captured camera image and a soccer field model. The presented method first detects reliable field lines from the camera image through clustering. Constructing a novel directional feature of the intersection points of the lines in both the camera image and the model, the presented method then finds matching pairs of these points between the image and the model. Finally, Homography matrix estimations and validations are performed using the obtained matching pairs, which can reduce the required number of Homography matrix calculations. Our presented method uses possible intersection points outside image for the point matching. This effectively improves robustness and accuracy of Homography estimation as demonstrated in experimental results.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021PCP0003/_p
Copy
@ARTICLE{e104-d_10_1563,
author={Kazuki KASAI, Kaoru KAWAKITA, Akira KUBOTA, Hiroki TSURUSAKI, Ryosuke WATANABE, Masaru SUGANO, },
journal={IEICE TRANSACTIONS on Information},
title={Robust and Efficient Homography Estimation Using Directional Feature Matching of Court Points for Soccer Field Registration},
year={2021},
volume={E104-D},
number={10},
pages={1563-1571},
abstract={In this paper, we present an efficient and robust method for estimating Homography matrix for soccer field registration between a captured camera image and a soccer field model. The presented method first detects reliable field lines from the camera image through clustering. Constructing a novel directional feature of the intersection points of the lines in both the camera image and the model, the presented method then finds matching pairs of these points between the image and the model. Finally, Homography matrix estimations and validations are performed using the obtained matching pairs, which can reduce the required number of Homography matrix calculations. Our presented method uses possible intersection points outside image for the point matching. This effectively improves robustness and accuracy of Homography estimation as demonstrated in experimental results.},
keywords={},
doi={10.1587/transinf.2021PCP0003},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Robust and Efficient Homography Estimation Using Directional Feature Matching of Court Points for Soccer Field Registration
T2 - IEICE TRANSACTIONS on Information
SP - 1563
EP - 1571
AU - Kazuki KASAI
AU - Kaoru KAWAKITA
AU - Akira KUBOTA
AU - Hiroki TSURUSAKI
AU - Ryosuke WATANABE
AU - Masaru SUGANO
PY - 2021
DO - 10.1587/transinf.2021PCP0003
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2021
AB - In this paper, we present an efficient and robust method for estimating Homography matrix for soccer field registration between a captured camera image and a soccer field model. The presented method first detects reliable field lines from the camera image through clustering. Constructing a novel directional feature of the intersection points of the lines in both the camera image and the model, the presented method then finds matching pairs of these points between the image and the model. Finally, Homography matrix estimations and validations are performed using the obtained matching pairs, which can reduce the required number of Homography matrix calculations. Our presented method uses possible intersection points outside image for the point matching. This effectively improves robustness and accuracy of Homography estimation as demonstrated in experimental results.
ER -
English
