Efficient multisensor fusion using multidimensional data association

We present the development of a multisensor fusion algorithm using multidim ensional data association for multitarget tracking. The work is motivated b y a large scale surveillance problem, where observations from multiple asyn chronous sensors with time-varying sampling intervals (electronically scann ed array (ESA) radars) are used for centralized fusion. The combination of multisensor fusion with multidimensional assignment is done so as to maximi ze the "time-depth," in addition to "sensor-width" for the number S of list s handled by the assignment algorithm. The standard procedure, which associ ates measurements from the most recently arrived S -1 frames to established tracks, can have, in the case of S sensors, a time-depth of zero. A new te chnique, which guarantees maximum effectiveness for an S-dimensional data a ssociation (S greater than or equal to 3), i.e., maximum time-depth (S - 1) for each sensor without sacrificing the fusion across sensors, is presente d. Using a sliding window technique (of length S), the estimates are update d after each frame of measurements. The algorithm provides a systematic app roach to automatic track formation, maintenance, and termination for multit arget tracking using multisensor fusion with multidimensional assignment fo r data association. Estimation results are presented for simulated data for a large scale air-to-ground target tracking problem.