Visual tracking using convolutional features with sparse coding

Visual object tracking has become one of the most active research topics in computer vision, and it has been applied in several commercial applications. Several visual trackers have been presented in the last two decades. They target different tracking objectives. Object tracking from a real-time vi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The Artificial intelligence review Ročník 54; číslo 5; s. 3349 - 3360
Hlavní autoři: Abbass, Mohammed Y., Kwon, Ki-Chul, Kim, Nam, Abdelwahab, Safey A., El-Samie, Fathi E. Abd, Khalaf, Ashraf A. M.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Dordrecht Springer Netherlands 01.06.2021
Springer
Springer Nature B.V
Témata:
Algorithms
Artificial Intelligence
Clutter
Computer assisted research
Computer Science
Computer vision
Feature extraction
Machine vision
Measurement
Occlusion
Optical tracking
Real time
Robustness
Sparse matrices
Support vector machines
Technology application
Tracking
Compressive sensing
Convolutional features
SVM
Object tracking
ISSN:0269-2821, 1573-7462
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Visual object tracking has become one of the most active research topics in computer vision, and it has been applied in several commercial applications. Several visual trackers have been presented in the last two decades. They target different tracking objectives. Object tracking from a real-time video is a challenging problem. Therefore, a robust tracker is required to consider many aspects of videos such as camera motion, occlusion, illumination effect, clutter, and similar appearance. In this paper, we propose an efficient object tracking algorithm that adaptively represents the object appearance using CNN-based features. A sparse measurement matrix is proposed to extract the compressed features for the appearance model without sacrificing the performance. We compress sample images of the foreground object and the background by the sparse matrix. When re-detection is needed, the tracking algorithm conducts an SVM classifier on the extracted features with online update in the compressed domain. A search strategy is proposed to reduce the computational burden in the detection step. Extensive simulations with a challenging video dataset demonstrate that the proposed tracking algorithm provides real-time tracking, while delivering substantially better tracking performance than those of the state-of-the-art techniques in terms of robustness, accuracy, and efficiency.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0269-2821
1573-7462
DOI:10.1007/s10462-020-09905-7