Assessing motion style errors in Ski jumping using inertial sensor devices

Heike Brock, Yuji Ohgi

研究成果: Article

4 引用 (Scopus)

抄録

Ski jumping is an expert sport that requires fine motor skills to guarantee the safe conduct of training and competition. In this paper, we therefore employed multiple inertial sensors to build and evaluate a framework for the assessment of jump errors and motion style. First, a large set of inertial ski jump motion captures were augmented, segmented, and transformed into multiple statistic and time-serial motion feature representations. All features were next used to learn and retrieve style error information from the jump segments under two classification strategies in a cross-validation cycle. Average accuracies of the error recognition indicated the applicability of the proposed system with error recognition rates between 60% and 75%, which should be considered sufficiently good under the present size and quality of the real life training data. Furthermore, the chosen signal-based motion features appeared to be better suited to extract and recognize style errors than the chosen kinematic induced features obtained using expensive postprocessing. This assumption could constitute important information for many related application systems. Therefore, it should be investigated whether such result can be generalized under different extracted features or further feature set compositions in the future.

元の言語English
記事番号7913696
ページ(範囲)3794-3804
ページ数11
ジャーナルIEEE Sensors Journal
17
発行部数12
DOI
出版物ステータスPublished - 2017 6 15

Fingerprint

skis
sensors
Sensors
sensorimotor performance
Ski jumps
education
Sports
Kinematics
kinematics
Statistics
statistics
cycles
Chemical analysis

ASJC Scopus subject areas

  • Instrumentation
  • Electrical and Electronic Engineering

これを引用

Assessing motion style errors in Ski jumping using inertial sensor devices. / Brock, Heike; Ohgi, Yuji.

:: IEEE Sensors Journal, 巻 17, 番号 12, 7913696, 15.06.2017, p. 3794-3804.

研究成果: Article

@article{53c740a30e5943149206101918411727,
title = "Assessing motion style errors in Ski jumping using inertial sensor devices",
abstract = "Ski jumping is an expert sport that requires fine motor skills to guarantee the safe conduct of training and competition. In this paper, we therefore employed multiple inertial sensors to build and evaluate a framework for the assessment of jump errors and motion style. First, a large set of inertial ski jump motion captures were augmented, segmented, and transformed into multiple statistic and time-serial motion feature representations. All features were next used to learn and retrieve style error information from the jump segments under two classification strategies in a cross-validation cycle. Average accuracies of the error recognition indicated the applicability of the proposed system with error recognition rates between 60{\%} and 75{\%}, which should be considered sufficiently good under the present size and quality of the real life training data. Furthermore, the chosen signal-based motion features appeared to be better suited to extract and recognize style errors than the chosen kinematic induced features obtained using expensive postprocessing. This assumption could constitute important information for many related application systems. Therefore, it should be investigated whether such result can be generalized under different extracted features or further feature set compositions in the future.",
keywords = "Inertial sensors, Kinematics, Motion analysis, Motor performance detection, Sensor applications, Sensor data processing",
author = "Heike Brock and Yuji Ohgi",
year = "2017",
month = "6",
day = "15",
doi = "10.1109/JSEN.2017.2699162",
language = "English",
volume = "17",
pages = "3794--3804",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "12",

}

TY - JOUR

T1 - Assessing motion style errors in Ski jumping using inertial sensor devices

AU - Brock, Heike

AU - Ohgi, Yuji

PY - 2017/6/15

Y1 - 2017/6/15

N2 - Ski jumping is an expert sport that requires fine motor skills to guarantee the safe conduct of training and competition. In this paper, we therefore employed multiple inertial sensors to build and evaluate a framework for the assessment of jump errors and motion style. First, a large set of inertial ski jump motion captures were augmented, segmented, and transformed into multiple statistic and time-serial motion feature representations. All features were next used to learn and retrieve style error information from the jump segments under two classification strategies in a cross-validation cycle. Average accuracies of the error recognition indicated the applicability of the proposed system with error recognition rates between 60% and 75%, which should be considered sufficiently good under the present size and quality of the real life training data. Furthermore, the chosen signal-based motion features appeared to be better suited to extract and recognize style errors than the chosen kinematic induced features obtained using expensive postprocessing. This assumption could constitute important information for many related application systems. Therefore, it should be investigated whether such result can be generalized under different extracted features or further feature set compositions in the future.

AB - Ski jumping is an expert sport that requires fine motor skills to guarantee the safe conduct of training and competition. In this paper, we therefore employed multiple inertial sensors to build and evaluate a framework for the assessment of jump errors and motion style. First, a large set of inertial ski jump motion captures were augmented, segmented, and transformed into multiple statistic and time-serial motion feature representations. All features were next used to learn and retrieve style error information from the jump segments under two classification strategies in a cross-validation cycle. Average accuracies of the error recognition indicated the applicability of the proposed system with error recognition rates between 60% and 75%, which should be considered sufficiently good under the present size and quality of the real life training data. Furthermore, the chosen signal-based motion features appeared to be better suited to extract and recognize style errors than the chosen kinematic induced features obtained using expensive postprocessing. This assumption could constitute important information for many related application systems. Therefore, it should be investigated whether such result can be generalized under different extracted features or further feature set compositions in the future.

KW - Inertial sensors

KW - Kinematics

KW - Motion analysis

KW - Motor performance detection

KW - Sensor applications

KW - Sensor data processing

UR - http://www.scopus.com/inward/record.url?scp=85021737115&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021737115&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2017.2699162

DO - 10.1109/JSEN.2017.2699162

M3 - Article

AN - SCOPUS:85021737115

VL - 17

SP - 3794

EP - 3804

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 12

M1 - 7913696

ER -