Kinect posture and gesture recognition

Sisinf Lab logo

Application description

Innovative analysis methods applied to data extracted by off-the-shelf peripherals can provide useful results in activity recognition without requiring large computational resources.

We propose a framework for automated posture and gesture detection, exploiting depth data from Microsoft Kinect. Novel features are:

  1. the adoption of Semantic Web technologies for posture and gesture annotation;
  2. the exploitation of non-standard inference services provided by an embedded matchmaker [1] to automatically detect postures and gestures>.
Particularly, the recognition problem is handled as a resource discovery, grounded on a semantic-based matchmaking [2]. An ontology for geometry-based semantic description of postures has been developed and encapsulated in a Knowledge Base (KB), also including several instances representing pose templates to be detected. 3D body model data detected by Kinect are pre-processed on-the-fly to identify key postures, i.e. unambiguous and not transient body positions. They typically correspond to the initial or final state of a gesture. Each key posture is then annotated adopting standard Semantic Web languages grounded on Description Logics (DL). Hence, non-standard inferences allows to compare the retrieved annotations with templates populating the Knowledge Base and a similarity-based ranking supports the discovery of the best matching posture. The ontology further allows to annotate a gesture from its component key postures, in order to enable recognition of gestures in a similar way.

Framework description

The framework has been implemented in a prototype and experimental tests have been carried out on a reference dataset. Results indicate good posture/gesture identification performance with respect to approaches based on machine learning.

Prototype user interface

  1. Real-time Kinect camera output with detected skeleton superimposed.
  2. Sematic annotation panel, with tree-like graphical representation of the reference ontology and annotation editing via drag-and-drop of classes and properties.
  3. Timeline with the sequence of recognized postures and gestures. They are processed by the embedded reasoner.
  4. Toolbar and settings.



  1. F. Scioscia, M. Ruta, G. Loseto, F. Gramegna, S. Ieva, A. Pinto, E. Di Sciascio, A mobile matchmaker for the Ubiquitous Semantic Web, International Journal on Semantic Web and Information Systems, Volume 10, Number 4, page 77-100, 2014.

  2. M. Ruta, E. Di Sciascio, F. Scioscia, Concept Abduction and Contraction in Semantic-based P2P Environments, Web Intelligence and Agent Systems, Volume 9, Number 3, page 179-207 - 2011.

Project coordinators

Valid XHTML 1.1   Valid CSS

:: hosted by SisInf Lab ::