Stroboscopic Image Synthesis of Sports Player from Hand-Held Camera Sequence

Kunihiro Hasegawa, Hideo Saito

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

Abstract

A method for synthesizing the stroboscopic image of a moving sports player from a hand-held camera sequence is proposed. In this method, a player is extracted from each frame of an input video sequence using a HOG-based people detector. After removing the bounding box of the extracted player from each frame, all frames are stitched together to generate a background image without the player. The player's area is then overlaid onto the stitched background image and a stroboscopic image of the player is synthesized. By using the bounding box of the player detected by HOG and by subtracting the images, computational speed and accuracy can be improved compared with the conventional method that segments the player's region. In addition to the stroboscopic image synthesis, we also remove the player's shadow to improve the appearance of the resultant stroboscopic image. Experimental results demonstrate the effectiveness of the proposed method.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Computer Vision
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages726-733
Number of pages8
Volume2016-February
ISBN (Print)9781467383905
DOIs
Publication statusPublished - 2016 Feb 11
Event15th IEEE International Conference on Computer Vision Workshops, ICCVW 2015 - Santiago, Chile
Duration: 2015 Dec 112015 Dec 18

Other

Other15th IEEE International Conference on Computer Vision Workshops, ICCVW 2015
CountryChile
CitySantiago
Period15/12/1115/12/18

Fingerprint

Sports
Cameras
Detectors

Keywords

  • Cameras
  • Feature extraction
  • Image generation
  • Length measurement
  • Position measurement
  • Sensors
  • Video sequences

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Hasegawa, K., & Saito, H. (2016). Stroboscopic Image Synthesis of Sports Player from Hand-Held Camera Sequence. In Proceedings of the IEEE International Conference on Computer Vision (Vol. 2016-February, pp. 726-733). [7406448] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW.2015.99

Stroboscopic Image Synthesis of Sports Player from Hand-Held Camera Sequence. / Hasegawa, Kunihiro; Saito, Hideo.

Proceedings of the IEEE International Conference on Computer Vision. Vol. 2016-February Institute of Electrical and Electronics Engineers Inc., 2016. p. 726-733 7406448.

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

Hasegawa, K & Saito, H 2016, Stroboscopic Image Synthesis of Sports Player from Hand-Held Camera Sequence. in Proceedings of the IEEE International Conference on Computer Vision. vol. 2016-February, 7406448, Institute of Electrical and Electronics Engineers Inc., pp. 726-733, 15th IEEE International Conference on Computer Vision Workshops, ICCVW 2015, Santiago, Chile, 15/12/11. https://doi.org/10.1109/ICCVW.2015.99
Hasegawa K, Saito H. Stroboscopic Image Synthesis of Sports Player from Hand-Held Camera Sequence. In Proceedings of the IEEE International Conference on Computer Vision. Vol. 2016-February. Institute of Electrical and Electronics Engineers Inc. 2016. p. 726-733. 7406448 https://doi.org/10.1109/ICCVW.2015.99
Hasegawa, Kunihiro ; Saito, Hideo. / Stroboscopic Image Synthesis of Sports Player from Hand-Held Camera Sequence. Proceedings of the IEEE International Conference on Computer Vision. Vol. 2016-February Institute of Electrical and Electronics Engineers Inc., 2016. pp. 726-733
@inproceedings{b18a492b61b0407d9fd6629cf92112bc,
title = "Stroboscopic Image Synthesis of Sports Player from Hand-Held Camera Sequence",
abstract = "A method for synthesizing the stroboscopic image of a moving sports player from a hand-held camera sequence is proposed. In this method, a player is extracted from each frame of an input video sequence using a HOG-based people detector. After removing the bounding box of the extracted player from each frame, all frames are stitched together to generate a background image without the player. The player's area is then overlaid onto the stitched background image and a stroboscopic image of the player is synthesized. By using the bounding box of the player detected by HOG and by subtracting the images, computational speed and accuracy can be improved compared with the conventional method that segments the player's region. In addition to the stroboscopic image synthesis, we also remove the player's shadow to improve the appearance of the resultant stroboscopic image. Experimental results demonstrate the effectiveness of the proposed method.",
keywords = "Cameras, Feature extraction, Image generation, Length measurement, Position measurement, Sensors, Video sequences",
author = "Kunihiro Hasegawa and Hideo Saito",
year = "2016",
month = "2",
day = "11",
doi = "10.1109/ICCVW.2015.99",
language = "English",
isbn = "9781467383905",
volume = "2016-February",
pages = "726--733",
booktitle = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Stroboscopic Image Synthesis of Sports Player from Hand-Held Camera Sequence

AU - Hasegawa, Kunihiro

AU - Saito, Hideo

PY - 2016/2/11

Y1 - 2016/2/11

N2 - A method for synthesizing the stroboscopic image of a moving sports player from a hand-held camera sequence is proposed. In this method, a player is extracted from each frame of an input video sequence using a HOG-based people detector. After removing the bounding box of the extracted player from each frame, all frames are stitched together to generate a background image without the player. The player's area is then overlaid onto the stitched background image and a stroboscopic image of the player is synthesized. By using the bounding box of the player detected by HOG and by subtracting the images, computational speed and accuracy can be improved compared with the conventional method that segments the player's region. In addition to the stroboscopic image synthesis, we also remove the player's shadow to improve the appearance of the resultant stroboscopic image. Experimental results demonstrate the effectiveness of the proposed method.

AB - A method for synthesizing the stroboscopic image of a moving sports player from a hand-held camera sequence is proposed. In this method, a player is extracted from each frame of an input video sequence using a HOG-based people detector. After removing the bounding box of the extracted player from each frame, all frames are stitched together to generate a background image without the player. The player's area is then overlaid onto the stitched background image and a stroboscopic image of the player is synthesized. By using the bounding box of the player detected by HOG and by subtracting the images, computational speed and accuracy can be improved compared with the conventional method that segments the player's region. In addition to the stroboscopic image synthesis, we also remove the player's shadow to improve the appearance of the resultant stroboscopic image. Experimental results demonstrate the effectiveness of the proposed method.

KW - Cameras

KW - Feature extraction

KW - Image generation

KW - Length measurement

KW - Position measurement

KW - Sensors

KW - Video sequences

UR - http://www.scopus.com/inward/record.url?scp=84962003906&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962003906&partnerID=8YFLogxK

U2 - 10.1109/ICCVW.2015.99

DO - 10.1109/ICCVW.2015.99

M3 - Conference contribution

AN - SCOPUS:84962003906

SN - 9781467383905

VL - 2016-February

SP - 726

EP - 733

BT - Proceedings of the IEEE International Conference on Computer Vision

PB - Institute of Electrical and Electronics Engineers Inc.

ER -