Work place ergonomics: pose estimation by 3D sensing

Problem statement

Work place ergonomics is the key factor of a healthy work place. Paying attention to ergonomic standards cannot only prevent back pain or postural deformity, but also vision problems and tensions. The existing 3D sensor fearless detects and tracks the position of an employee during the work and offers possibilities for improving the actual position.


Currently there is only one pose detected, but various poses are required. One major task of this thesis is to extend the number of poses as raised shoulders, body rotations and combinations of different poses and angles. In order to personalize the service face detection might be applied: since the whole system relies on 3d data only, a face detector based on range data should be developed. Recent advancements in thermal imaging allow the usage of thermal sensor in similar applications. Within this thesis thermal imaging for pose estimation should be investigated.


  • Review literature: study the state of the art
  • Select 2 methods based on quality criteria, as well as ease of implementation and training
  • Include 3d data as well as thermal images
  • Explore provided extensive (non-public) training and test data set
  • Implement training and test algorithms
  • Evaluate methods based on appropriate scores and quality criteria
  • Written report/thesis and final presentation


  • Basic knowledge in computer vision
  • Basic experience in Python and OpenCV
  • Interest in Machine Learning, maths, statistics


  • Pramerdorfer, M. Kampel, J. Heering: “3D Upper-Body Pose Estimation and Classification for Detecting Unhealthy Sitting Postures at the Workplace”; Vortrag: Fourth International Conference on Informatics and Assistive Technologies for Health-Care, Medical Support and Wellbeing – HEALTHINFO 2019, Valencia, Spanien; 24.11.2019 – 28.11.2019; in: “HEALTHINFO 2019 The Fourth International Conference on Informatics and Assistive Technologies for Health-Care, Medical Support and Wellbeing”, (2019), ISBN: 978-1-61208-759-7; S. 49 – 53.
  • Schörghuber, M. Humenberger, M. Gelautz: “Camera-based pose estimation in dynamic environments – concept and status”;
    Poster: Prairie Artificial Intelligence Summer School, Grenoble; 02.07.2018 – 06.07.2018.
  • Xu, Ning et al. “Deep Image Matting.” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)

Send me an email for more information: