Frequency Line Tracking Algorithms

Autor: A. K. Steele, R. F. Barrett, R. L. Streit
Rok vydání: 1989
Předmět:
Zdroj: Underwater Acoustic Data Processing ISBN: 9789401075275
DOI: 10.1007/978-94-009-2289-1_56
Popis: This paper has several purposes. The first purpose is to compare via simulation the performance of six different frequency line tracking algorithms (FLTA’s) when used in conjunction with a simple threshold detector. The second purpose is show that the probabilistic data association (PDA) method for handling multiple detections is not limited to the Kaiman filter context in which it has hitherto been presented. In particular, we present a PDA alpha-beta tracker that handles multiple detections without sacrificing algorithmic simplicity. The third purpose is to discuss a new tracker based on hidden Markov models (HMM’s). An important and intrinsic feature of the HMM tracker is that it initiates and terminates tracks automatically.
Databáze: OpenAIRE