Title : 
Fish-eye stereo based on the Taylor model
         
        
        
            Author_Institution : 
College of Computer and Information Engineering, Zhejiang Gongshang University, Hangzhou, China
         
        
        
        
        
        
            Abstract : 
In this paper, a method of fish-eye stereo base on the Taylor model is proposed. The fish-eye stereo cameras are first calibrated based on the Taylor model. Then, the mapping between the pin-hole perspective view and the distorted view of fish-eye camera is deduced and the fish-eye images are expanded to the perspective images, the intrinsic parameters of ideal perspective camera are also acquired. The extrinsic parameters are calculated accurately using a planar pattern placed in the common field of views of two fish-eye cameras, and stereo rectification is proceed based on these extrinsic parameters. Experimental results show that the proposed method is simple, flexible and effective.
         
        
            Keywords : 
Calibration; Cameras; Computational modeling; Lenses; Mathematical model; Robot vision systems; Stereo vision; Fish-eye lens; Taylor model; epipolar rectification; stereo vision;
         
        
        
        
            Conference_Titel : 
Information Science and Engineering (ICISE), 2010 2nd International Conference on
         
        
            Conference_Location : 
Hangzhou, China
         
        
            Print_ISBN : 
978-1-4244-7616-9
         
        
        
            DOI : 
10.1109/ICISE.2010.5691642