Evaluation of Neck Motion Due to Change in Working Velocity Based on Feature Extraction with Motion Division

  • Kazuki HiranaiEmail author
  • Atsushi Sugama
  • Takanori Chihara
  • Akihiko Seo
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 824)


In recent year, the evaluation method of human motion to clarify the usability is needed because it is a hard task to assess the subjective evaluation of usability of product and the comfort of the environment. This study aimed to analyze neck motion using feature extraction with motion division and clarify the relationship between neck motion and workability. We propose the motion division method based on the calculation of probability density function from the Gaussian distribution. The algorithm being proposed uses the analysis of the measured data by an experiment. As part of the experiment, each participant was instructed to gaze at a target while in the sitting posture. The working posture of each participant was measured to evaluate the effects of working velocity on the position of the target. The numbers of extracted feature point decreased with the decreasing working velocity. The normal working velocity condition maximized the number of extracted feature points. Moreover, participants answered the best subjective workability under normal conditions. These results show that increasing the number of extracted feature points may improve workability.


Motion division method Feature extraction Workability evaluation 



This work was supported by JSPS KAKENHI Grant Number JP16K01247.


  1. 1.
    McCauley-Bell PR (2002) Ergonomics in virtual environment. In: Stanney KM (ed) Handbook of virtual environments, design, implementation, and applications. Lawrence Erlbaum Associates, London, pp 807–812Google Scholar
  2. 2.
    Baber C, Knight J, Haniff D, Cooper L (1999) Ergonomics of wearable computer. Mob Netw Appl 4:15–21CrossRefGoogle Scholar
  3. 3.
    Wang L, Hu W, Tan T (2003) Recent developments in human motion analysis. Pattern Recogn 36(3):585–601CrossRefGoogle Scholar
  4. 4.
    Chaquet JM, Carmona EJ, Fernández-Caballero A (2013) A survey of video datasets for human action and activity recognition. Comput Vis Image Underst 117:633–659CrossRefGoogle Scholar
  5. 5.
    Min J, Kasturi R, Camps O (2008) Extraction and temporal segmentation of multiple motion trajectories in human motion. Image Vis Comput 26:1621–1635CrossRefGoogle Scholar
  6. 6.
    Lau N, Wong B, Chow D (2009) Motion segmentation method for hybrid characteristic on human motion. J Biomech 42:436–442CrossRefGoogle Scholar
  7. 7.
    Yu X, Liu W, Xing W (2017) Behavioral segmentation for human motion capture data based on graph cut method. J Vis Lang Comput 43:50–59CrossRefGoogle Scholar
  8. 8.
    Bauer CM, Rast FM, Ernst MJ, Meichtry A, Kool J, Rissanen SM, Kankaanpaa M (2017) The effects of muscle fatigue and low back pain on lumber movement variability and complexity. J Electromyogr Kinesiol 33:94–102CrossRefGoogle Scholar
  9. 9.
    Cortes N, Onate J, Morrison S (2014) Differential effects of fatigue on movement variability. Gait Posture 39(3):888–893CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Kazuki Hiranai
    • 1
    Email author
  • Atsushi Sugama
    • 2
  • Takanori Chihara
    • 3
  • Akihiko Seo
    • 4
  1. 1.Graduate School of System DesignTokyo Metropolitan UniversityHinoJapan
  2. 2.Center for Risk Management ResearchNational Institute of Occupational Safety and HealthKiyoseJapan
  3. 3.Institute for Frontier Science InitiativeKanazawa UniversityKanazawaJapan
  4. 4.Faculty of System DesignTokyo Metropolitan UniversityHinoJapan

Personalised recommendations