Kinect-based medical image exploration
An open-source system for a controller-free, highly interactive exploration of medical images. By using a Microsoft Xbox KinectTM as the only input device, the system’s user interface allows users to interact at a distance through hand and arm gestures. The system features interaction techniques specifically designed for the deviceless exploration of medical imaging data. Since the user interface is touch-free and does not require complex calibration steps, it is suitable for use in operating rooms, where non-sterilizable devices cannot be used.
In the system's controller-free interface all the interaction commands are mapped to gestures, which can be executed at a distance from the display without touching it. Moreover, filters have been implemented to reduce the noise in the device signal, to increase the accuracy of the remote pointing and to filter hand tremors during all the interaction tasks. The user's body is represented as a stick figure, which consists of line segments linked by joints. The motion of the joints provides the key to motion estimation and recognition of the whole figure.
Recognized gestures have both static elements (the user assumes a certain pose or configuration) and dynamic elements (with pre-stroke, stroke, and post-stroke phases). Some gestures also have both static and dynamic elements. Static postures, represented by a single image, are used to discriminate between possible actions. Dynamic gestures, characterized by the spatio-temporal motion structures in image sequences, are used to further discriminate between actions.
- L. Gallo, A.P. Placitelli, and M. Ciampi, “Controller-free exploration of medical image data: experiencing the Kinect”, in IEEE CMBS '11: Proceedings of the 24th IEEE International Symposium on Computer-Based Medical Systems, (Piscataway, NJ, USA), IEEE, 2011. doi: 10.1109/CBMS.2011.5999138