29,712 Hits in 5.9 sec

STResNet_CF Tracker: The deep spatiotemporal features learning for correlation filter based robust visual object tracking

Zhengyu Zhu, Bing Liu, Yunbo Rao, Qiao Liu, Rui Zhang
2019 IEEE Access  
This paper presents a novel method for visual object tracking based on spatiotemporal feature combined with correlation filters.  ...  Finally, our spatiotemporal fusion feature from STResNet appearance model is incorporated into the correlation filter for robust visual object tracking.  ...  filter of which are combined by late fusion for visual object tracking.  ... 
doi:10.1109/access.2019.2903161 fatcat:uas76gauobcspkjwvuvy6wpevi

Learning Temporal Regularized Correlation Filter Tracker with Spatial Reliable Constraint

Lei Pu, Xinxi Feng, Zhiqiang Hou
2019 IEEE Access  
INDEX TERMS Visual tracking, correlation filter, convolutional neural network, spatial constraint, temporal regularization.  ...  In this paper, we construct the spatial reliable map with deep features from Convolutional Neural Network, then the map is used to adjust the filter support to the part of the object suitable for tracking  ...  CORRELATION FILTER Correlation filters have recently attracted considerable attention in visual tracking due to computational efficiency and robustness.  ... 
doi:10.1109/access.2019.2922416 fatcat:mzli7ni3bfes5bb6f7rstypkvy

Learning adaptive spatial–temporal regularized correlation filters for visual tracking

Jianwei Zhao, Yangxiao Li, Zhenghua Zhou
2021 IET Image Processing  
This paper proposes an effective tracking method, named adaptive spatial-temporal regularized correlation filter (ASTRCF) tracker, based on the popular adaptive spatially regularized correlation filter  ...  Recently, there have been many visual tracking methods based on correlation filters.  ...  It mainly learns the correlation filter with a set of extracted features using fast Fourier transform (FFT), then predicts the position of the object in the next frame by the learned correlation filter  ... 
doi:10.1049/ipr2.12150 fatcat:dcx6cmuaknggvpydtcygazcdqi

Second-Order Spatial-Temporal Correlation Filters for Visual Tracking

Yufeng Yu, Long Chen, Haoyang He, Jianhui Liu, Weipeng Zhang, Guoxia Xu
2022 Mathematics  
Discriminative correlation filters (DCFs) have been widely used in visual object tracking, but often suffer from two problems: the boundary effect and temporal filtering degradation.  ...  Meanwhile, the spatial–temporal regularization was integrated to develop a robust model in tracking with complex appearance variations.  ...  Acknowledgments: We greatly thank the Reviewers and Editors for the insightful comments and suggestions. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/math10050684 fatcat:5aqumuqzfnefrfty3wmmjh64nm

Learning Padless Correlation Filters for Boundary-Effect Free Tracking

Dongdong Li, Gongjian Wen, Yangliu Kuai, Fatih Porikli
2018 IEEE Sensors Journal  
Among different DCF variants, spatially regularized discriminative correlation filters (SRDCFs) demonstrate excellent performance in suppressing boundary effects induced from circularly shifted training  ...  Compared with SRDCF that penalizes filter values with spatial regularization weights, PCF directly guarantee zero filter values outside the target bounding box with a binary mask.  ...  Discriminative Correlation Filters Discriminative Correlation Filters (DCF) are initially developed for the object detection task [22] and are introduced into visual tracking until recent years.  ... 
doi:10.1109/jsen.2018.2861912 fatcat:yrud7uixufaaheitsk7fg4ozly

Correlation Tracking via Spatial-Temporal Constraints and Structured Sparse Regularization

Dan Tian, Shouyu Zang, Binbin Tu
2021 IEEE Access  
[1] develop a multi-task deep dual correlation filters based method for visual tracking, which takes full advantage of the multi-level features of deep networks. Li et al.  ...  SPATIAL-TEMPORAL CONSTRAINTS AND STRUCTURED SPARSE REGULARIZATION FOR DCF TRACKING A.  ... 
doi:10.1109/access.2021.3086821 fatcat:nrjp7qxlirazzltbjouq7tqdaq

Adaptive Spatial-Temporal Regularization for Correlation Filters Based Visual Object Tracking

Fei Chen, Xiaodong Wang
2021 Symmetry  
Recently, Discriminative Correlation Filters (DCF) have shown excellent performance in visual object tracking.  ...  In this paper, we propose a novel framework that employs adaptive spatial regularization and temporal regularization to learn reliable filters in both spatial and temporal domains for tracking.  ...  [13] proposed kernelized correlation filters (KCF) based on linear and kernel ridge regression for fast visual object tracking.  ... 
doi:10.3390/sym13091665 fatcat:ybgcts4xybbbfjzbfczmwrzfpq

Hierarchical Convolutional Features for Visual Tracking

Chao Ma, Jia-Bin Huang, Xiaokang Yang, Ming-Hsuan Yang
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
Visual object tracking is challenging as target objects often undergo significant appearance changes caused by deformation, abrupt motion, background clutter and occlusion.  ...  We interpret the hierarchies of convolutional layers as a nonlinear counterpart of an image pyramid representation and exploit these multiple levels of abstraction for visual tracking.  ...  Tracking by Correlation Filters. Correlation filters for visual tracking have attracted considerable attention due to its high computational efficiency with the use of fast Fourier transforms.  ... 
doi:10.1109/iccv.2015.352 dblp:conf/iccv/MaHYY15 fatcat:gd2v4prsmvh75n5wk5536hubta

Convolutional Features for Correlation Filter Based Visual Tracking

Martin Danelljan, Gustav Hager, Fahad Shahbaz Khan, Michael Felsberg
2015 2015 IEEE International Conference on Computer Vision Workshop (ICCVW)  
Visual object tracking is a challenging computer vision problem with numerous real-world applications. This paper investigates the impact of convolutional features for the visual tracking problem.  ...  We propose to use activations from the convolutional layer of a CNN in discriminative correlation filter based tracking frameworks.  ...  We acknowledge the NVIDA corporation for support in the form of different GPU hardware units.  ... 
doi:10.1109/iccvw.2015.84 dblp:conf/iccvw/DanelljanHKF15 fatcat:hwduztmchbch7h4kltl52hr334

Learning Spatial–Temporal Background-Aware Based Tracking

Peiting Gu, Peizhong Liu, Jianhua Deng, Zhi Chen
2021 Applied Sciences  
In this paper, a spatial–temporal regularization module based on BACF (background-aware correlation filter) framework is proposed, which is performed by introducing a temporal regularization to deal effectively  ...  Discriminative correlation filter (DCF) based tracking algorithms have obtained prominent speed and accuracy strengths, which have attracted extensive attention and research.  ...  Acknowledgments: The authors would like to thank all of the reviewers for their constructive comments. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app11188427 fatcat:ecwy6lflg5bkppm2byyanuoquy

Learning an Orientation and Scale Adaptive Tracker with Regularized Correlation Filters

Ke Tan, Zhenzhong Wei
2019 IEEE Access  
To address the issue, we propose a novel Orientation and Scale adaptive tracker with Regularized Correlation Filters (OSRCF) for visual tracking.  ...  Spatial and temporal constraints are very important for correlation filter (CF)-based trackers.  ...  [30] propose a spatially regularized correlation filter by penalizing filter values outside the object boundaries.  ... 
doi:10.1109/access.2019.2912527 fatcat:ha2xyn7ljnayvbnszj4aufalpi

Robust Visual Tracking with Spatial Regularization Kernelized Correlation Filter Constrained by A Learning Spatial Reliability Map

Qianbo Liu, Guoqing Hu, Md Mojahidul Islam
2019 IEEE Access  
In this paper, we extend the kernelized correlation filter (CF) for robust tracking by introducing spatial regularization components to penalize the CF coefficients.  ...  INDEX TERMS Feature fusion, model update mechanism, spatial regularization components, spatial reliability map.  ...  [13] proposed spatially regularized discriminative correlation filters for tracking (SRDCF), in which the authors employed a spatial regularization component to penalize correlation filter coefficients  ... 
doi:10.1109/access.2019.2902216 fatcat:jat7hihzdfajnfauobmsh6qrzu

Visual Tracking via Adaptive Spatially-Regularized Correlation Filters

Kenan Dai, Dong Wang, Huchuan Lu, Chong Sun, Jianhua Li
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
First, this adaptive spatial regularization scheme could learn an effective spatial weight for a specific object and its appearance variations, and therefore result in more reliable filter coefficients  ...  In this work, we propose a novel adaptive spatiallyregularized correlation filters (ASRCF) model to simultaneously optimize the filter coefficients and the spatial regularization weight.  ...  This paper is supported in part by National Natural Science Foundation of China Nos. 61872056, 61771088, 61751212, 61725202 and 61829102, and in part by the Fundamental Research Funds for the Central Universities  ... 
doi:10.1109/cvpr.2019.00480 dblp:conf/cvpr/Dai0LSL19 fatcat:yi44ojlcz5bnzewydnvy4jgwsi

Sampling Operator to Learn the Scalable Correlation Filter for Visual Tracking

Minkyu Lee, Taeoh Kim, Yuseok Ban, Eungyeol Song, Sangyoun Lee
2019 IEEE Access  
INDEX TERMS Visual tracking, correlation filter, sampling operator, scalability.  ...  The correlation filter is suitable for tracking on account of its low computational complexity and promising performance.  ...  [20] proposed spatially regularized discriminant correlation filters (SRDCF) to learn large filters in large windows by using a spatial regularizer. Mueller et al.  ... 
doi:10.1109/access.2019.2892429 fatcat:ppwaownm25d55clrx3od4dy2lu

Visual Tracking via Spatially Aligned Correlation Filters Network [chapter]

Mengdan Zhang, Qiang Wang, Junliang Xing, Jin Gao, Peixi Peng, Weiming Hu, Steve Maybank
2018 Lecture Notes in Computer Science  
Keywords: visual tracking · spatial transformer network · deep learning · correlation filters network *The first two authors contributed equally to this work.  ...  It enables correlation filters to work on well-aligned samples for better tracking.  ...  The visual tracking of translating objects has been successfully tackled by recent correlation filters (CF) based approaches [10, 18] .  ... 
doi:10.1007/978-3-030-01219-9_29 fatcat:2j2swhpzmba5jm3q6usv3cuniq
« Previous Showing results 1 — 15 out of 29,712 results