.png){kind=icon}
.png){kind=icon}
Return
Collaborative Convolution Operators for Real-Time Coarse-to-Fine Tracking
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2018.2800699.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Discriminative correlation filter (DCF) has attracted enormous popularity among the tracking community. Standard DCF based trackers easily achieve real-time tracking speed but significantly suffer from the boundary effects. Recently, spatially regularized or constrained correlation filters tackle the problem of boundary effects at the sacrifice of the closed-form element-wise solution. In this paper, we cope with boundary effects from a novel perspective and present a coarse-to-fine tracking (CTFT) framework which breaks the task of visual tracking into two stages. In the first stage, CTFT locates the target coarsely with a deep convolution operator in a large search area. In the second stage, CTFT performs a fine-grained search of the target with a shallow convolution operator around the initial location in the first stage. With this two-stage tracking framework, CTFT holds a large target search area and maintains the efficient element-wise solution of standard DCF. Compared with state-of-the-art deep trackers, CTFT makes a good balance between computational efficiency and accuracy. Extensive experimental results on OTB2013 and OTB2015 demonstrate that CTFT maintains real-time performance at an average tracking speed of 35.8 fps and achieves favorable performance against state-of-the-art trackers.
Keywords:
Collaborative tracking
correlation tracking
coarse-to-fine tracking
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W