Robust Visual Object Tracking using Context-Aware Dual Correlation Filter
|
|
Author:
|
V.RAMALAKSHMI KANTHIMATHI, DR. M. GERMANUS ALEX
|
Abstract:
|
Visual object tracking is one of challenging tasks in the field of computer vision with a wide range of applications, such as
video surveillance, autonomous vehicles, human-machine interaction, and robotics. Correlation Filter (CF) based
trackers have gained much attention in the recent years, because of their excellent tracking performance and higher
throughput. In this paper, we present a variant of Correlation Filter for object tracking called Context-Aware Dual
Correlation Filter (CADCF). Through experimental validation on a benchmarking 100 videos (OTB-100), we showed
that the proposed tracker achieves superior accuracy and real time performance compared to the state-of-art trackers.
|
Keyword:
|
Visual object tracking, correlation filter, context-aware, kernels.
|
EOI:
|
-
|
DOI:
|
-
|
Download:
|
Request For Article
|
|
|