Surveillance systems capable of autonomously monitoring vast areas are an emerging trend, particularly when wide-angle cameras\nare combined with pan-tilt-zoom (PTZ) cameras in a master-slave configuration. The use of fish-eye lenses allows the master\ncamera to maximize the coverage area while the PTZ acts as a foveal sensor, providing high-resolution images of regions of interest.\nDespite the advantages of this architecture, the mapping between image coordinates and pan-tilt values is the major bottleneck\nin such systems, since it depends on depth information and fish-eye effect correction. In this paper, we address these problems\nby exploiting geometric cues to perform height estimation. This information is used both for inferring 3D information from a\nsingle static camera deployed on an arbitrary position and for determining lens parameters to remove fish-eye distortion. When\ncompared with the previous approaches, our method has the following advantages: (1) fish-eye distortion is corrected without\nrelying on calibration patterns; (2) 3D information is inferred from a single static camera disposed on an arbitrary location of the\nscene.
Loading....