Design of an Automatic Target Recognation algorithm

In this study, first, an Automated Target Recognition/Tracking (ATR, ATT) system is analyzed, developed and simulated on Matlab environment. Second, a new edge detection method is proposed which is obtained by combining two common edge detection algorithms. Finally, it is shown that Freeman chain codding can be used in feature extraction stage of an ATR system. The system is tested for many different image databases, except for its classification and decision making part, which is still under development, and the results are verified by human eye. Note that, with the development of the classification part, the results will be able to verified with an objective criteria. On the other hand, the designed ATR system is planed to be optimized for an hardware and implemented on an FPGA device in a future work.

[2]  Chein-I Chang,et al.  Automatic spectral target recognition in hyperspectral imagery , 2003 .

[3]  Bir Bhanu,et al.  Automatic Target Recognition: State of the Art Survey , 1986, IEEE Transactions on Aerospace and Electronic Systems.

[4]  Aydin Alatan,et al.  Rotation, scale and translation invariant automatic target recognition based on Fourier-Mellin transform and bispectrum for satellite imagery , 2010, 2010 IEEE 18th Signal Processing and Communications Applications Conference.

[5]  Krista A. Ehinger,et al.  SUN database: Large-scale scene recognition from abbey to zoo , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  C. W. Swonger,et al.  A prospectus for automatic target recognition , 1989 .

[7]  Hongjun Wang,et al.  Real-Time Object Tracking System on FPGAs , 2011, 2011 Symposium on Application Accelerators in High-Performance Computing.

[8]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..