Adaptive Visual Target Tracking Based on Label Consistent K-Svd Sparse Coding and Kernel Particle Filter

We propose an adaptive visual target tracking algorithm based on Label-Consistent K -Singular Value Decomposition (LC-KSVD) dictionary learning. To construct target templates, local patch features are sampled from foreground and background of the target. LC-KSVD then is applied to these local patche...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) s. 1633 - 1637
Hlavní autoři: Yang, Jinlong, Chen, Xiaoping, Hu, Yu Hen, Liu, Jianjun
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.04.2018
Témata:
Classification algorithms
Dictionaries
dictionary learning
Feature extraction
Kernel
label consistent K-SVD
Lighting
Machine learning
particle filter
Particle filters
Signal processing algorithms
sparse coding
Target tracking
Visual target tracking
Visualization
ISSN:2379-190X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We propose an adaptive visual target tracking algorithm based on Label-Consistent K -Singular Value Decomposition (LC-KSVD) dictionary learning. To construct target templates, local patch features are sampled from foreground and background of the target. LC-KSVD then is applied to these local patches to simultaneously estimate a set of low-dimension dictionary and classification parameters (CP). To track the target over time, a kernel particle filter (KPF) is proposed that integrates both local and global motion information of the target. An adaptive template updating scheme is also developed to improve the robustness of the tracker. Experimental results demonstrate superior performance of the proposed algorithm over state-of-art visual target tracking algorithms in scenarios that include occlusion, background clutter, illumination change, target rotation and scale changes.
ISSN:2379-190X
DOI:10.1109/ICASSP.2018.8462675