Recognition of complex human behaviours using 3D imaging for intelligent surveillance applications
2016
We introduce a system that exploits 3-D imaging technology as an enabler for the robust recognition of the human form. We combine this with pose and feature recognition capabilities from which we can recognise high-level human behaviours. We propose a hierarchical methodology for the recognition of complex human behaviours, based on the identification of a set of atomic behaviours, individual and sequential poses (e.g. standing, sitting, walking, drinking and eating) that provides a framework from which we adopt time-based machine learning techniques to recognise complex behaviour patterns.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
15
References
1
Citations
NaN
KQI