Correlation filter tracking with adaptive proposal selection for accurate scale estimation
This work addresses scale estimation for visual object tracking, offering an incremental improvement in efficiency and accuracy for tracking applications.
The paper tackled the problem of redundant proposals degrading performance and speed in correlation filter trackers by proposing an adaptive proposal selection algorithm based on color similarity, which achieved favorable results against state-of-the-art trackers on benchmark datasets.
Recently, some correlation filter based trackers with detection proposals have achieved state-of-the-art tracking results. However, a large number of redundant proposals given by the proposal generator may degrade the performance and speed of these trackers. In this paper, we propose an adaptive proposal selection algorithm which can generate a small number of high-quality proposals to handle the problem of scale variations for visual object tracking. Specifically, we firstly utilize the color histograms in the HSV color space to represent the instances (i.e., the initial target in the first frame and the predicted target in the previous frame) and proposals. Then, an adaptive strategy based on the color similarity is formulated to select high-quality proposals. We further integrate the proposed adaptive proposal selection algorithm with coarse-to-fine deep features to validate the generalization and efficiency of the proposed tracker. Experiments on two benchmark datasets demonstrate that the proposed algorithm performs favorably against several state-of-the-art trackers.