Metrics for evaluating the performance of joint-transform-correlation-based target recognition and tracking algorithms

The performance of target detection and tracking algorithms generally depends on the signature, clutter, and noise that are usually present in the input scene. To evaluate the effectiveness of a given algorithm, it is necessary to develop performance metrics based on the input plane as well as output plane information. We develop two performance metrics for assessing the effects of input plane data on the performance of detection and tracking algorithms by identifying three regions of operation—excellent, average, and risky intervals. To evaluate the performance of a given algorithm based on the output plane information, we utilize several metrics that use primarily correlation peak intensity and clutter information. Since the fringe-adjusted joint transform correlation (JTC) was found to yield better correlation output compared to alternate JTC algorithms, we investigate the performance of two fringe-adjusted JTC (FJTC)-based detection and tracking algorithms using several metrics involving the correlation peak sharpness, signal-to-noise ratio, and distortion invariance. The aforementioned input and output plane metrics are used to evaluate the results for both single/multiple target detection and tracking algorithms using real life forward-looking infrared (FLIR) video sequences.

[1]  D A Gregory,et al.  Effects of fringe binarization of multiobject joint transform correlation. , 1989, Applied optics.

[2]  Abhijit Mahalanobis,et al.  Signal-to-clutter measure for measuring automatic target recognition performance using complimentary eigenvalue distribution analysis , 2003 .

[3]  Bhagavatula Vijaya Kumar,et al.  Performance of the extended maximum average correlation height (EMACH) filter and the polynomial distance classifier correlation filter (PDCCF) for multiclass SAR detection and classification , 2002, SPIE Defense + Commercial Sensing.

[4]  Mohammad A. Karim,et al.  Improved correlation discrimination in a multi-object bipolar joint transform correlator , 1992 .

[5]  Mohammad S. Alam,et al.  Automatic target tracking using global motion compensation and fringe-adjusted joint transform correlation , 2004, SPIE Optics + Photonics.

[6]  A Mahalanobis,et al.  Optimal trade-off synthetic discriminant function filters for arbitrary devices. , 1994, Optics letters.

[7]  Karl S Gudmundsson,et al.  Sub-imaging technique to improve phase only filter search capability. , 2003, Applied optics.

[8]  J L Horner,et al.  Metrics for assessing pattern-recognition performance. , 1992, Applied optics.

[9]  B. Kumar,et al.  Performance measures for correlation filters. , 1990, Applied optics.

[10]  Philippe Réfrégier,et al.  Bayesian theory for target location in noise with unknown spectral density , 1999 .

[11]  Philippe Réfrégier,et al.  DECISION THEORY APPROACH TO NONLINEAR JOINT-TRANSFORM CORRELATION , 1998 .

[12]  Mohammad S. Alam.  Deblurring using fringe-adjusted joint transform correlation , 1998 .

[13]  P Refregier.  Optimal trade-off filters for noise robustness, sharpness of the correlation peak, and Horner efficiency. , 1991, Optics letters.

[14]  Eliezer Oron,et al.  Precision tracking with segmentation for imaging sensors , 1993 .

[15]  Abhijit Mahalanobis,et al.  Comparative study of maximum average correlation height filter variants using ladar imagery , 2003 .

[16]  Mohammad S. Alam,et al.  Infrared image registration and high-resolution reconstruction using multiple translationally shifted aliased video frames , 2000, IEEE Trans. Instrum. Meas..

[17]  D. Casasent,et al.  Correlation synthetic discriminant functions. , 1986, Applied optics.

[18]  Mohammad S. Alam,et al.  Performance evaluation for cluttered infrared image based on fringe-adjusted joint transform correlator , 2004, SPIE Defense + Commercial Sensing.

[19]  Abdullah Bal,et al.  Automatic target tracking in FLIR image sequences , 2004, SPIE Defense + Commercial Sensing.

[20]  S. Richard F. Sims,et al.  Signal-to-clutter measure for ATR performance comparison , 1997, Defense, Security, and Sensing.

[21]  Mohammad S. Alam,et al.  Invariant FJTC-based multitarget tracking in FLIR video sequences , 2004, SPIE Optics + Photonics.