An adaptable system for RGB-D based human body detection and pose estimation: incorporating attached props

H. Haggag, M. Hossny, S. Nahavandi, O. Haggag

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

16 Citations (Scopus)


One of the biggest challenges of RGB-D posture tracking is separating appendages such as briefcases, trolleys, and backpacks from the human body. Markerless motion tracking relies on segmenting each depth frame to a finite set of body parts. This is achieved via supervised learning by assigning each pixel to a certain body part. The training image set for the supervised learning are usually synthesised using popular motion capture databases and an ensemble of 3D models covering a wide range of anthropometric characteristics. In this paper, we propose a novel method for generating training data of human postures with attached objects. The results have shown a significant increase in body-part classification accuracy for subjects with props from 60% to 94% using the generated image set.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Systems, Man, and Cybernetics - Conference Proceedings
EditorsShun-Feng Su
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)9781509018970, 9781509018192
ISBN (Print)9781509018987
Publication statusPublished - 2016
Externally publishedYes
EventIEEE International Conference on Systems, Man and Cybernetics 2016 - Budapest, Hungary
Duration: 9 Oct 201612 Oct 2016 (Proceedings)


ConferenceIEEE International Conference on Systems, Man and Cybernetics 2016
Abbreviated titleSMC 2016
Internet address


  • Kinect
  • Pixel Labelling
  • Props
  • RGB-D

Cite this