People Tracking and Posture Recognition for Human-Robot Interaction

The paper deals with a system for simultaneous people tracking and posture recognition in cluttered environments in the context of human-robot interaction. We adopt no particular assumptions on the movement of a person nor on its appearance, making the system suitable to several real-world applications. The system can be roughly subdivided into two highly correlated phases: tracking and recognition. The tracking is concerned with establishing coherent relations of the same subject between frames. We adopted a version of particle filters known as Condensation algorithm due to its robustness in highly cluttered environments. The recognition phase adopts a modified eigenspace technique in order to classify between several different postures. The system has demonstrated to be robust in different working conditions and permits to exploit a rich interaction between a human user and a robotic system by means of a set of natural gestures.