US 6,982,667 B2
Method for target-tracking of objects
Robert Artebrant, Lund (Sweden); and Andreas Tyrberg, Hägersten (Sweden)
Assigned to SAAB AB, Linkoping (Sweden)
Appl. No. 10/481,788
PCT Filed Jun. 19, 2002, PCT No. PCT/SE02/01181
§ 371(c)(1), (2), (4) Date Dec. 23, 2003,
PCT Pub. No. WO03/003044, PCT Pub. Date Jan. 09, 2003.
Claims priority of application No. 012328 (SE), filed on Jun. 28, 2001.
Prior Publication US 2004/0150551 A1, Aug. 05, 2004
Int. Cl. G01S 13/72 (2006.01)
U.S. Cl. 342—95 6 Claims
OG exemplary drawing
 
1. A method for target-tracking of objects via observations from a sensor, wherein a geographical region within which at least one object is present is divided into a predetermined number of states, the method comprising:
dividing the geographical region into partially overlapping subregions so that adjacently disposed subregions all contain a share of states in common in at least the portions of the adjacently disposed subregions that partially overlap;
initiating target-tracking in one subregion, whereupon a first observation is associated with the object and the probable state of the object is estimated; and
for each new time interval, a new observation is chosen for which a new state is estimated, whereupon the estimated sequence of states in the subregion is updated, and the target-tracking in a new subregion is based on the state history for the states that are shared in common with the previous subregions upon transition between two adjacent subregions, which transition is initiated when the probability that the object has moved to a new subregion exceeds a certain predetermined value.