Tracking with classification-aided multiframe data association

In most conventional tracking systems, only the target kinematic information from, for example, a radar or sonar or an electro-optical sensor, is used in measurement-to-track association. Target class information, which is typically used in postprocessing, can also be used to improve data association to give better tracking accuracy. The use of target class information in data association can improve discrimination by yielding purer tracks and preserving their continuity. In this paper, we present the simultaneous use of target classification information and target kinematic information for target tracking. The approach presented integrates target class information into the data association process using the 2-D (one track list and one measurement list) as well as multiframe (one track list and multiple measurement lists) assignments. The multiframe association likelihood is developed to include the classification results based on the "confusion matrix" that specifies the accuracy of the target classifier. The objective is to improve association results using class information when the kinematic likelihoods are similar for different targets, i.e., there is ambiguity in using kinematic information alone. Performance comparisons with and without the use of class information in data association are presented on a ground target tracking problem. Simulation results quantify the benefits of classification-aided data association for improved target tracking, especially in the presence of association uncertainty in the kinematic measurements. Also, the benefit of 5-D (or multiframe) association versus 2-D association is investigated for different quality classifiers. The main contribution of this paper is the development of the methodology to incorporate exactly the classification information into multidimensional (multiframe) association.

[1]  Torbjörn Wigren Target-type probability combining algorithms for multisensor tracking , 2001, SPIE Defense + Commercial Sensing.

[2]  Yakov Bar-Shalom,et al.  Multitarget-Multisensor Tracking: Principles and Techniques , 1995 .

[3]  Kuo-Chu Chang,et al.  Target identification with Bayesian networks in a multiple hypothesis tracking system , 1997 .

[4]  Jeffery R. Layne Automatic Target Recognition and Tracking Filter , 1998 .

[5]  K. Kastella Joint multitarget probabilities for detection and tracking , 1997 .

[6]  Lang Hong,et al.  Local motion feature aided ground moving target tracking with GMTI and HRR measurements , 2005, IEEE Transactions on Automatic Control.

[7]  Oliver E. Drummond Integration of features and attributes into target tracking , 2000, SPIE Defense + Commercial Sensing.

[8]  Lang Hong,et al.  Wavelets feature aided tracking (WFAT) using GMTI/HRR data , 2003, Signal Process..

[9]  Krishna R. Pattipati,et al.  IMM estimation for multitarget-multisensor air traffic surveillance , 1997 .

[10]  Y. Bar-Shalom,et al.  A new relaxation algorithm and passive sensor data association , 1992 .

[11]  Samuel S. Blackman,et al.  Design and Analysis of Modern Tracking Systems , 1999 .

[12]  Oliver E. Drummond,et al.  Feature, attribute, and classification aided target tracking , 2001 .

[13]  Peter S. Maybeck,et al.  Application of sequence comparison techniques to multisensor data fusion and target recognition , 1993, Proceedings of 32nd IEEE Conference on Decision and Control.

[14]  Erik Blasch,et al.  Simultaneous feature-based identification and track fusion , 1998, Proceedings of the 37th IEEE Conference on Decision and Control (Cat. No.98CH36171).

[15]  J. Schmitz,et al.  Model-based range extent for feature aided tracking , 2000, Record of the IEEE 2000 International Radar Conference [Cat. No. 00CH37037].

[16]  Y. Bar-Shalom,et al.  A generalized S-D assignment algorithm for multisensor-multitarget state estimation , 1997, IEEE Transactions on Aerospace and Electronic Systems.

[17]  D. Bertsekas The auction algorithm: A distributed relaxation method for the assignment problem , 1988 .