Multiple hypotheses tracking based distributed fusion using decorrelated pseudo measurement sequence

A joint probabilistic data association based algorithm for multi-target tracking in clutter using the distributed tracking architecture has been proposed recently. The algorithm uses the decorrelated state estimates or equivalent pseudo measurements. This paper extends the previous approach to the m...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2004 American Control Conference Proceedings; Volume 5 of 6 Ročník 5; s. 4750 - 4751 vol.5
Hlavní autoři: Mallick, M., Pao, L.Y., Chang, K.C.
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: Piscataway NJ IEEE 01.01.2004
Evanston IL American Automatic Control Council
Témata:
Additive noise
Applied sciences
Computational complexity
Computer architecture
Computer errors
Computer science; control theory; systems
Control theory. Systems
Covariance matrix
Decorrelation
Distributed computing
Exact sciences and technology
Measurement errors
Modelling and identification
State estimation
Target tracking
Target tracking
Probabilistic approach
Clutter
Distributed algorithm
ISBN:9780780383357, 0780383354
ISSN:0743-1619
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:A joint probabilistic data association based algorithm for multi-target tracking in clutter using the distributed tracking architecture has been proposed recently. The algorithm uses the decorrelated state estimates or equivalent pseudo measurements. This paper extends the previous approach to the multi-target tracking problem in clutter with probability of detection less than unity using the track-oriented multiple hypotheses tracking framework. We present multiple hypotheses distributed tracking algorithms for track initialization, gating, hypothesis generation, track update, computation of track likelihood, formation of global hypothesis, and pruning using the pseudo measurement formulation.
Bibliografie:SourceType-Scholarly Journals-2
ObjectType-Feature-2
ObjectType-Conference Paper-1
content type line 23
SourceType-Conference Papers & Proceedings-1
ObjectType-Article-3
ISBN:9780780383357
0780383354
ISSN:0743-1619
DOI:10.23919/ACC.2004.1384062