Efficient Illumination Insensitive Object Tracking by Normalized Gradient Matching

We propose a novel tracking algorithm by minimizing the sum-of-squared differences (SSD) between the normalized image gradients of the template image and the input image from the test image sequence. The proposed tracking algorithm is efficient to implement since it is based on the framework of the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE signal processing letters Ročník 14; číslo 12; s. 944 - 947
Hlavní autoři: Guopu Zhu, Guopu Zhu, Shuqun Zhang, Shuqun Zhang, Xijun Chen, Xijun Chen, Changhong Wang, Changhong Wang
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.12.2007
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Application software
Computational efficiency
Computer vision
Illumination
Image sequences
Inverse
Inverse compositional algorithm
Lighting
Matching
Minimization methods
normalized gradient matching
Object recognition
Pattern matching
Signal processing
Space technology
template matching
Testing
Tracking
visual tracking
template matching
Inverse compositional algorithm
visual tracking
normalized gradient matching
ISSN:1070-9908, 1558-2361
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We propose a novel tracking algorithm by minimizing the sum-of-squared differences (SSD) between the normalized image gradients of the template image and the input image from the test image sequence. The proposed tracking algorithm is efficient to implement since it is based on the framework of the inverse compositional algorithm, a computationally efficient tracking technique. The experiments show that the proposed tracking algorithm is superior to the intensity-based inverse compositional algorithm in tracking objects under varying illumination conditions.
Bibliografie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
content type line 23
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2007.903277