Activity recognition with Kinect

This Master thesis work consists of the design and implementation of a novel context-aware system for deictic gestures interaction with smart environments. The proposed system cannot only recognize and track the inhabitants, but also allows for the recognition of users' postures, deictic gestures and previously trained gestures based on HMM in real-time recognition process. Multiple Microsoft Kinect depth cameras have been used to acquire the data and the framework offers the possibility to a user to improve the system accuracy.
Student: Julien Tscherrig
Year: 2012



Website of the project

Project Information