Fast Tracking Algorithm Based on Spatial Regularization Correlation Filter

To solve the problem of the redundant number of training samples in a correlation filter-based tracking algorithm, the training samples were implicitly extended by circular shifts of the given target patches, and all the extended samples were used as negative samples for the fast online learning of...

Celý popis

Uloženo v:
Podrobná bibliografie
Hlavní autoři: Caihong Liu, Mayire Ibrayim, Askar Hamdulla
Médium: Artigo
Jazyk:Inglês
Vydáno: MDPI AG 2022-04-01
Edice:Information
Témata:
discriminative correlation filter
spatial regularization
boundary effects
constraint optimization
occlusion detection
On-line přístup:https://www.mdpi.com/2078-2489/13/4/184
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!

Podobné jednotky