Estimating the position of a moving target in the polar frame of reference has been a major problem in the conventional tracking systems. The commonly used sensor equipment provides the position of target in polar coordinates i.e. in range and azimuth (or bearing) angle with respect to the sensor location. The use of simple Kalman filter increases the error in this case. For more accurate tracking, the Converted Measurement Kalman filter (CMKF) is used which can account for the inaccuracies in tracking using polar coordinates. Simulations were performed tracking the target with CMKF. It does not proffer well in missed detection and false alarm scenarios. So the tracking was improved by associating Global nearest Neighbour algorithm (GNN) algorithm with the CMKF. Later the simulations depict the inconsistency of GNN based CMKF in a dense missed detection and false alarm scenarios. So an improved algorithm in track estimation is used to solve the dense missed detections or continuous false alarm problem. Thus, through simulation, it was realized that GNN based improved CMKF is able to give a better tracking. Finally Wiener filtering is used to smoothen the tracking.
Data fusion techniques combine data from multiple sensors and related information from associated databases, to achieve improved accuracies and more specific inferences than could be achieved by the use of a single sensor alone. Objective of this paper is to implement data association algorithms for target tracking based on range only measurements given by multiple sensors located at different positions using a TMS processor, first in a single target scenario and then in a multi-target scenario where ranges obtained from each sensor are required to be associated to the correct targets. In case of a single target multi-sensor (STMS) scenario, Gauss-Newton iterative method based Data Fusion is carried out to determine the target position. In case of multitarget multi-sensor (MTMS) scenario, each radar provides data regarding range of targets as detected by it. Considering all possible combinations of ranges, the probable fused target positions are estimated using Gauss-Newton technique. The near approximated fused position is then determined from probable positions by Minimum Mean Square Estimation (MMSE).Index Terms-TMS processor, Gauss-Newton method, Multilateration, STMS, MTMS.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.