Title : 
Complexity analysis of ATR algorithms based on invariants
         
        
            Author : 
Arnold, D. Gregory ; Sturtz, Kirk
         
        
            Author_Institution : 
Target Recognition Branch, Air Force Res. Lab., OH, USA
         
        
        
        
        
        
            Abstract : 
Research in the calculation and exploitation of geometric object/image relations suggests new approaches to automatic target recognition (ATR). The resulting conceptual advances have efficiently solved the geometry problem and have transformed the ATR problem into a correspondence problem. This paper provides an analysis of the elementary algorithms which exploit object/image relations as a basis for object recognition. The goal is to develop an understanding for the critical components to address for developing a practical system. 3D laser radar is used as an example
         
        
            Keywords : 
computational complexity; image matching; object recognition; optical radar; radar imaging; 3D laser radar; ATR algorithms; automatic target recognition; complexity analysis; correspondence problem; geometric object/image relations; geometry problem; invariants; object recognition; Aerospace electronics; Algorithm design and analysis; Electrical capacitance tomography; Geometry; Image analysis; Image recognition; Kirk field collapse effect; Object recognition; Sensor phenomena and characterization; Target recognition;
         
        
        
        
            Conference_Titel : 
Computer Vision Beyond the Visible Spectrum: Methods and Applications, 2000. Proceedings. IEEE Workshop on
         
        
            Conference_Location : 
Hilton Head, SC
         
        
            Print_ISBN : 
0-7695-0640-2
         
        
        
            DOI : 
10.1109/CVBVS.2000.855247