Semi complex navigation with an active optical gesture sensor

This paper presents the methods of diversified touchless interactions between a user and a mobile platform utilizing the optical gesture sensor. The sensor uses 8 photodiodes to measure the reflected light in the active mode (using embedded LEDs) or it measures shadows caused by fingers in the passive mode. Several algorithms were implemented: automatic mode switching, adaptive illumination level compensation, resolution improvements using model to data fitting, etc. The embedded processor delivers recognized static or dynamic gesture codes, location of fingers, etc. Thanks to the sparse construction of the sensor and number of the detectors, it handles a few discrete but also continuous gestures. The most important features of the sensor are: low power and computational requirements in comparison to vision based gesture recognition systems and that it is a septic safe interface. It was embedded into smart glasses platform.