A framework for face detection on Central Catadioptric Systems

This paper presents a method of adaptation of the well-known Viola and Jones´ face detector to Central Catadioptric Systems. The performance of this detector is well-known and has been well studied. Our purpose is not to evaluate the intrinsic limits of the Viola and Jones´ algorithm but to evaluate the impact of central projection systems on the algorithm´s behavior. 360-degree field of view sensors offer interesting capabilities for Human-Robot Interface. They do not require users to be in a specific part of the robot´s surrounding environment. Most of the time, such interfaces imply face detection. Unified models can be used to calibrate central projection systems resulting in a single set of parameters. In order to apply perspective-like detection techniques, we apply rectification techniques to transform wrapped images into perspective panoramic images. We demonstrate that spherical projection gives better results than cylindrical projection. We introduce a model of a person´s location with respect to the sensor. Spatial limitations and the impact of the interpolation method during the unwrapping procedure are also discussed.