A method for evaluating performance of joint tracking and classification

Joint tracking and classification (JTC) is rapidly gaining momentum recently. Algorithms have been proposed for this problem. However, performance of tracking and classification has been evaluated separately without considering their interdependence. In this paper, we propose a joint measure, named joint probability score (JPS), to account for tracking error, misclassification and their interdependence. The basic idea of JPS is to measure the difference between the cumulative distribution functions (CDFs) of the ideal JTC and the one to be evaluated. Moreover, performance of tracking and classification can be unified by applying CDF. The proposed method is unit free and positive definite. Also, it has close connections with stochastic dominance and the so-called continuous ranked probability score. Two examples illustrating our JPS are presented. The results demonstrate that JPS reflects well the joint performance of tracking and classification.

[1]  Yu Liu,et al.  Recursive joint decision and estimation based on generalized Bayes risk , 2011, 14th International Conference on Information Fusion.

[2]  X. Rong Li,et al.  Joint tracking and classification of extended object based on support functions , 2014, 17th International Conference on Information Fusion (FUSION).

[3]  X. Rong Li,et al.  Joint tracking and classification of extended object using random matrix , 2013, Proceedings of the 16th International Conference on Information Fusion.

[4]  X. Rong Li,et al.  Extended object tracking and classification based on recursive joint decision and estimation , 2013, Proceedings of the 16th International Conference on Information Fusion.

[5]  LI X.RONG,et al.  Evaluation of estimation algorithms part I: incomprehensive measures of performance , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[6]  X. Rong Li,et al.  Optimal bayes joint decision and estimation , 2007, 2007 10th International Conference on Information Fusion.

[7]  X. Rong Li,et al.  Joint tracking and classification based on recursive joint decision and estimation using multi-sensor data , 2014, 17th International Conference on Information Fusion (FUSION).

[8]  G. Brier.  VERIFICATION OF FORECASTS EXPRESSED IN TERMS OF PROBABILITY , 1950 .

[9]  Thia Kirubarajan,et al.  Estimation with Applications to Tracking and Navigation: Theory, Algorithms and Software , 2001 .

[10]  A. Raftery,et al.  Strictly Proper Scoring Rules, Prediction, and Estimation , 2007 .

[11]  Ming Yang,et al.  Joint tracking and classification based on bayes joint decision and estimation , 2007, 2007 10th International Conference on Information Fusion.

[12]  Subhash Challa,et al.  Joint target tracking and classification using radar and ESM sensors , 2001 .

[13]  H. Hersbach.  Decomposition of the Continuous Ranked Probability Score for Ensemble Prediction Systems , 2000 .

[14]  H. Levy.  Stochastic Dominance: Investment Decision Making under Uncertainty , 2010 .

[15]  X.R. Li,et al.  An efficient Bayesian algorithm for joint target tracking and classification , 2004, Proceedings 7th International Conference on Signal Processing, 2004. Proceedings. ICSP '04. 2004..