Ball 3D Trajectory Reconstruction without Preliminary Temporal and Geometrical Camera Calibration

Shogo Miyata, Hideo Saito, Kosuke Takahashi, Dan Mikami, Mariko Isogawa, Hideaki Kimata

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

2 Citations (Scopus)

Abstract

This paper proposes a method for reconstructing 3D ball trajectories by using multiple temporally and geometrically uncalibrated cameras. To use cameras to measure the trajectory of a fast-moving object, such as a ball thrown by a pitcher, the cameras must be temporally synchronized and their position and orientation should be calibrated. In some cases, these conditions cannot be met, e.g., one cannot geometrically calibrate cameras when one cannot step into a baseball stadium. The basic idea of the proposed method is to use a ball captured by multiple cameras as a corresponding point. The method first detects a ball. Then, it estimates temporal difference between cameras. After that, the ball positions are used as corresponding points for geometrically calibrating the cameras. Experiments using actual pitching videos verify the effectiveness of our method.

Original languageEnglish
Title of host publicationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
PublisherIEEE Computer Society
Pages164-169
Number of pages6
Volume2017-July
ISBN (Electronic)9781538607336
DOIs
Publication statusPublished - 2017 Aug 22
Event30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 - Honolulu, United States
Duration: 2017 Jul 212017 Jul 26

Other

Other30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
CountryUnited States
CityHonolulu
Period17/7/2117/7/26

Fingerprint

Cameras
Trajectories
Calibration
Stadiums
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Miyata, S., Saito, H., Takahashi, K., Mikami, D., Isogawa, M., & Kimata, H. (2017). Ball 3D Trajectory Reconstruction without Preliminary Temporal and Geometrical Camera Calibration. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 (Vol. 2017-July, pp. 164-169). [8014760] IEEE Computer Society. https://doi.org/10.1109/CVPRW.2017.26

Ball 3D Trajectory Reconstruction without Preliminary Temporal and Geometrical Camera Calibration. / Miyata, Shogo; Saito, Hideo; Takahashi, Kosuke; Mikami, Dan; Isogawa, Mariko; Kimata, Hideaki.

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. Vol. 2017-July IEEE Computer Society, 2017. p. 164-169 8014760.

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

Miyata, S, Saito, H, Takahashi, K, Mikami, D, Isogawa, M & Kimata, H 2017, Ball 3D Trajectory Reconstruction without Preliminary Temporal and Geometrical Camera Calibration. in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. vol. 2017-July, 8014760, IEEE Computer Society, pp. 164-169, 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017, Honolulu, United States, 17/7/21. https://doi.org/10.1109/CVPRW.2017.26
Miyata S, Saito H, Takahashi K, Mikami D, Isogawa M, Kimata H. Ball 3D Trajectory Reconstruction without Preliminary Temporal and Geometrical Camera Calibration. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. Vol. 2017-July. IEEE Computer Society. 2017. p. 164-169. 8014760 https://doi.org/10.1109/CVPRW.2017.26
Miyata, Shogo ; Saito, Hideo ; Takahashi, Kosuke ; Mikami, Dan ; Isogawa, Mariko ; Kimata, Hideaki. / Ball 3D Trajectory Reconstruction without Preliminary Temporal and Geometrical Camera Calibration. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. Vol. 2017-July IEEE Computer Society, 2017. pp. 164-169
@inproceedings{1091372b7d6a4994b5bc3f02b76a6d54,
title = "Ball 3D Trajectory Reconstruction without Preliminary Temporal and Geometrical Camera Calibration",
abstract = "This paper proposes a method for reconstructing 3D ball trajectories by using multiple temporally and geometrically uncalibrated cameras. To use cameras to measure the trajectory of a fast-moving object, such as a ball thrown by a pitcher, the cameras must be temporally synchronized and their position and orientation should be calibrated. In some cases, these conditions cannot be met, e.g., one cannot geometrically calibrate cameras when one cannot step into a baseball stadium. The basic idea of the proposed method is to use a ball captured by multiple cameras as a corresponding point. The method first detects a ball. Then, it estimates temporal difference between cameras. After that, the ball positions are used as corresponding points for geometrically calibrating the cameras. Experiments using actual pitching videos verify the effectiveness of our method.",
author = "Shogo Miyata and Hideo Saito and Kosuke Takahashi and Dan Mikami and Mariko Isogawa and Hideaki Kimata",
year = "2017",
month = "8",
day = "22",
doi = "10.1109/CVPRW.2017.26",
language = "English",
volume = "2017-July",
pages = "164--169",
booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Ball 3D Trajectory Reconstruction without Preliminary Temporal and Geometrical Camera Calibration

AU - Miyata, Shogo

AU - Saito, Hideo

AU - Takahashi, Kosuke

AU - Mikami, Dan

AU - Isogawa, Mariko

AU - Kimata, Hideaki

PY - 2017/8/22

Y1 - 2017/8/22

N2 - This paper proposes a method for reconstructing 3D ball trajectories by using multiple temporally and geometrically uncalibrated cameras. To use cameras to measure the trajectory of a fast-moving object, such as a ball thrown by a pitcher, the cameras must be temporally synchronized and their position and orientation should be calibrated. In some cases, these conditions cannot be met, e.g., one cannot geometrically calibrate cameras when one cannot step into a baseball stadium. The basic idea of the proposed method is to use a ball captured by multiple cameras as a corresponding point. The method first detects a ball. Then, it estimates temporal difference between cameras. After that, the ball positions are used as corresponding points for geometrically calibrating the cameras. Experiments using actual pitching videos verify the effectiveness of our method.

AB - This paper proposes a method for reconstructing 3D ball trajectories by using multiple temporally and geometrically uncalibrated cameras. To use cameras to measure the trajectory of a fast-moving object, such as a ball thrown by a pitcher, the cameras must be temporally synchronized and their position and orientation should be calibrated. In some cases, these conditions cannot be met, e.g., one cannot geometrically calibrate cameras when one cannot step into a baseball stadium. The basic idea of the proposed method is to use a ball captured by multiple cameras as a corresponding point. The method first detects a ball. Then, it estimates temporal difference between cameras. After that, the ball positions are used as corresponding points for geometrically calibrating the cameras. Experiments using actual pitching videos verify the effectiveness of our method.

UR - http://www.scopus.com/inward/record.url?scp=85030228158&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030228158&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2017.26

DO - 10.1109/CVPRW.2017.26

M3 - Conference contribution

AN - SCOPUS:85030228158

VL - 2017-July

SP - 164

EP - 169

BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017

PB - IEEE Computer Society

ER -