ROI Pooled Correlation Filters for Visual Tracking

Discriminative correlation filter (DCF) has achieved promising performance in visual tracking for its high efficiency and high accuracy. However, DCF trackers usually suffer from some challenges, such as boundary effects and appearance changes. In this paper, we propose a novel correlation tracking method via spatial-temporal constraints and structured sparse regularization. Firstly, we introduce the background-aware selection strategy to extract real negative examples, and penalize the filter coefficients close to the boundary locations for spatial protection, both of which can alleviate the boundary effects. Secondly, we restrict the filters with structured sparse regularization to handle the local appearance changes, and exploit temporal consistent constraint on the filters to address the global appearance changes. Finally, we employ the alternative direction method of multipliers to optimize our correlation tracking model. In our optimization framework, we combine grayscale, color names, histogram of orientation gradient with deep features for appearance learning to improve the discrimination. Meanwhile, we penalize spatial constraint and structured sparse regularization alternatively based on occlusion detection to enhance processing efficiency. The qualitative and quantitative experiments are conducted on the OTB dataset. Experimental results demonstrate that the proposed tracker has better performance than other state-of-theart trackers.INDEX TERMS Object tracking, correlation filter, spatial-temporal constraints, structured sparse regularization, deep feature This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication.

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Correlation Tracking via Spatial-Temporal Constraints and Structured Sparse Regularization

Tian

Zang

2021

“…To further assess our tracker, we follow the settings in ECO [11] and combine deep features with hand-crafted features. We compare our proposed tracker with recent state-of-the-art trackers using deep features including ASRCF [36] , RPCF [37] , MDNet [38] , LADCF_DEEP [33] , ECO_DEEP [11] , CCOT_DEEP [10] , SiamRPN [3] , DaSiamRPN [39] , STRCF_DEEP [34] , GFS_DCF [23] , TFCR [40] and SiamBAN [4] . Fig.9 shows the precision and success plots of 13 trackers in terms of OPE rule on OTB2013.…”

Section: Comparision With Trackers Using Deep Features On Otbmentioning

confidence: 99%

Adaptive and Complementary Correlation Filter With Dynamic Contextual Constraints

et al. 2020

Correlation filter-based trackers have gained more and more attention because of their great performance and relative high tracking speed. However, this kind of trackers may suffer model drifting due to learning limited background information during filter training. This may lead to tracking failures in some complex scenes, such as background clutter, deformation, illumination variation and so on. In this paper, we propose an adaptive and complementary correlation filter with dynamic contextual constraints. First, we introduce contextual information around the target as a dynamic constrained term to alleviate model drifting in complex scenes, the optimal function of which can be solved by iterative method. Then, we integrate a color histogram-based tracker to compensate the inaccurate tracking of correlation filtering. In addition, we present metrics to combine the two complementary trackers with adaptive fusion coefficients. Finally, extensive experiments on OTB2013, OTB2015, VOT2016 and UAV123 benchmark datasets demonstrate that our tracker can improve the performance of our baseline and can perform favorably against some stateof-the-art trackers.

“…Zhang et al [55] proposed an end-to-end deep architecture to incorporate geometric transformations into a CF based network and tackle the issue of boundary effects and aspect ratio variations in CF based trackers, ensuring an accurate motion estimation inferred from the consistently optimized network. Sun et al [56] developed a novel region-of-interest (ROI) pooled CF tracker for robust visual tracking. Meanwhile this paper proposed an efficient joint training formula for the proposed CF tracker and derived the Fourier solvers for efficient model training.…”

Section: Introductionmentioning

confidence: 99%

Robust Visual Tracking via Multilayer CaffeNet Features and Improved Correlation Filtering

Xiao

Di-fu

2019

For problems related to the robust tracking of visual objects in various challenging tracking conditions, a robust visual tracking method based on multilayer convolutional features and correlation filtering is proposed. To solve the problems of mean deviation and insufficient discrimination ability in traditional convolutional neural networks (CNN), this study proposes randomized parametric rectified linear units (RPReLU) as the activation function. Meanwhile, the zero-setting operation of weights in the traditional dropout process occurs randomly and fails to discriminate the features with different weights, which leads to a low learning efficiency. Therefore, this study proposes an improved dropout method based on a support vector machine (SVM), which provides a selective dropout rate to increase the manual orientation and improve the learning efficiency of the dropout process. In addition, traditional CNN trackers only employ the output of the last layer, which can effectively capture semantic features but not spatial features. To solve this problem, we propose to use the rich features of the multiple convolution layers of CaffeNet as the target representation. Furthermore, we propose an improved correlation filter to further improve the tracking performance and improve the tracker's capability of dealing with scale changes, which effectively solves the problem of adaptive estimating of target size. The extensive experimental evaluations have been carried out through the OTB2015, VOT2016 and VOT2018 datasets, proving that the proposed method is very effective in dealing with a variety of challenging factors.INDEX TERMS Convolutional neutral network, correlation filter, target tracking, computer vision technology.