A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Filters
Robust Visual Object Tracking via Sparse Representation and Reconstruction
[chapter]
2013
Lecture Notes in Computer Science
To address these challenges, this paper proposes a new approach for robust visual object tracking via sparse representation and reconstruction, where two main contributions are devoted in terms of object ...
Visual object tracking plays an essential role in vision based applications. ...
In this paper, we implemented a visual object tracking approach named as SR 2 KF tracker by integrating the sparse representation and reconstruction into a Kalman filter framework. ...
doi:10.1007/978-3-642-40246-3_35
fatcat:3nq7asro7bdx7ayngndel3jugy
Metric Learning Based Structural Appearance Model for Robust Visual Tracking
2014
IEEE transactions on circuits and systems for video technology (Print)
Index Terms-Appearance modeling, multiple instance metric learning, multiscale max pooling, object tracking, sparse coding. ...
In this paper, we advocate an approach to visual tracking that seeks an appropriate metric in the feature space of sparse codes and propose a metric learning based structural appearance model for more ...
Sparse representation based appearance modeling has received considerable attention in the visual tracking community. ...
doi:10.1109/tcsvt.2013.2291283
fatcat:y4y552vhbbcz7j22355ythgs6u
Author Index
2010
2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Visual Object Tracking using Adaptive Correlation Filters Workshop: Quantifying How Lighting and Focus Affect Face Recognition Performance Fu, Xingdou Reconstruction of Display and Eyes from a Single Image ...
Isoperimetric Cut on a Directed Graph
Liu, Qingshan
Image Retrieval via Probabilistic Hypergraph Ranking
Exploring Facial Expression with Compositional Features
Liu, Shaohui
Visual Tracking via ...
doi:10.1109/cvpr.2010.5539913
fatcat:y6m5knstrzfyfin6jzusc42p54
Visual Tracking Using Strong Classifier and Structural Local Sparse Descriptors
2015
IEEE transactions on multimedia
Sparse coding methods have achieved great success in visual tracking, and we present a strong classifier and structural local sparse descriptors for robust visual tracking. ...
Index Terms-Local descriptor, sparse representation, strong classifier, visual tracking. ...
[24] proposed a visual tracking decomposition for robust object tracking and applied different types of feature templates for object representation. Zhou et al. ...
doi:10.1109/tmm.2015.2463221
fatcat:ktqcg4shc5cizpu56cvcs6ulhq
Feature Selection Tracking Algorithm Based on Sparse Representation
2015
Mathematical Problems in Engineering
In order to enhance the robustness of visual tracking algorithm in complex environment, a novel visual tracking algorithm based on multifeature selection and sparse representation is proposed. ...
Finally, candidate targets are linearly reconstructed via sparse representation and the sparse equation is solved by using APG method to obtain the state of the target. ...
Agarwal and Roth [2] have achieved good results in object recognition via sparse representation. ...
doi:10.1155/2015/684370
fatcat:hwukizgmvjbhrbho4fi22v3evq
Sparse-Dense Motion Modelling and Tracking for Manipulation without Prior Object Models
[article]
2022
arXiv
pre-print
While the dense tracking enables interaction with these models, the sparse tracking makes this robust against fast movements and allows to redetect already modelled objects. ...
Using the motion of objects in a scene, our approach segments rigid entities from the scene and continuously tracks them to create a dense and sparse model of the object and the environment. ...
the ability to directly segment objects of interest via visual motion cues and the ability to redetect previously seen objects for long-term tracking. ...
arXiv:2204.11923v1
fatcat:smxbtnwjlzdwtkosw23jlm5bye
Boosting-Based Visual Tracking Using Structural Local Sparse Descriptors
[chapter]
2015
Lecture Notes in Computer Science
This paper develops an online algorithm based on sparse representation and boosting for robust object tracking. ...
Local descriptors of a target object are represented by pooling some sparse codes of its local patches, and an Adaboost classifier is learned using the local descriptors to discriminate target from background ...
In this paper, we present an online visual object tracking algorithm using local sparse appearance representation and an Adaboost classifier. ...
doi:10.1007/978-3-319-16814-2_34
fatcat:53j6vbvj6rbq5pxorwonrobwmm
Robust Object Tracking via Multi-block and Sparsity-Based Representation
2015
International Journal of Knowledge Engineering-IACSIT
Extensive experiments on challenging sequences show that the robust tracking achieved by our algorithm. Index Terms-Visual tracking, sparse representation, multi-block. ...
In this paper, we propose a robust object tracking algorithm based on classifier, multi-block and local sparse coding with multiple discriminative dictionary. ...
L1 tracker [5] apply sparse representation to visual tracking and deal with occlusions via trivial templates. The sample with minimal reconstruction errors is regarded as tracking result. ...
doi:10.7763/ijke.2015.v1.13
fatcat:nqqpk2avdbfrxfflcf2lvoie6q
Visual Object Tracking Based on 2DPCA and ML
2013
Mathematical Problems in Engineering
We present a novel visual object tracking algorithm based on two-dimensional principal component analysis (2DPCA) and maximum likelihood estimation (MLE). ...
Firstly, we introduce regularization into the 2DPCA reconstruction and develop an iterative algorithm to represent an object by 2DPCA bases. ...
Visual Object Tracking Model Based on 2DPCA and MLE: The Theory of 2DPCA 2.1. The Theory of 2DPCA. ...
doi:10.1155/2013/404978
fatcat:hlqtbqa3gjhvzouzwq7vslbdci
Online discriminative dictionary learning for visual tracking
2014
IEEE Winter Conference on Applications of Computer Vision
In this work, we propose a tracking framework based on sparse representation and online discriminative dictionary learning. ...
By associating dictionary items with label information, the learned dictionary is both reconstructive and discriminative, which better distinguishes target objects from the background. ...
[20] was the first to apply sparse representations to visual tracking. ...
doi:10.1109/wacv.2014.6836014
dblp:conf/wacv/YangJD14
fatcat:berk5tx4qzgnhiakrcdhx22ed4
Multi-cue Visual Tracking Using Robust Feature-Level Fusion Based on Joint Sparse Representation
2014
2014 IEEE Conference on Computer Vision and Pattern Recognition
To address this issue in multicue visual tracking, this paper proposes a new joint sparse representation model for robust feature-level fusion. ...
The proposed method dynamically removes unreliable features to be fused for tracking by using the advantages of sparse representation. As a result, robust tracking performance is obtained. ...
The current tracking result of the reliable visual cue k can be reconstructed by the information in R only, i.e. ...
doi:10.1109/cvpr.2014.156
dblp:conf/cvpr/LanMY14
fatcat:umpvciq73jfq3c7bzbuyu7amz4
Online-Learning Structural Appearance Model for Robust Visual Tracking
[chapter]
2013
Lecture Notes in Computer Science
Our appearance model employs structural feature pooling over the local sparse codes of an object region to obtain a robust object representation. ...
Existing tracking algorithms often build an representation for the tracked object, and perform self-updating of the object representation with examples from recently tracking results. ...
Conclusion We have proposed a robust appearance modeling method for visual tracking via a structural object representation strategy and online metric learning. ...
doi:10.1007/978-3-642-42057-3_5
fatcat:vqjorfrl7bcp5fi3yuq3pfia5e
Patchwise object tracking via structural local sparse appearance model
[article]
2018
arXiv
pre-print
In this paper, we propose a robust visual tracking method which exploits the relationships of targets in adjacent frames using patchwise joint sparse representation. ...
Evaluations on recent challenging benchmark show that our tracking method outperforms the state-of-the-art trackers. ...
INTRODUCTION Visual object tracking is one of the significant areas in machine vision, which can be applied to motion analysis, augmented reality, vehicle navigation, and robotics. ...
arXiv:1803.06141v1
fatcat:otmtesaiuve55olqiz6eppvppy
Visual Target Tracking Algorithm via Multi-scale Block and Sparse Representation
2015
International Journal of Signal Processing, Image Processing and Pattern Recognition
In this paper, a robust visual tracking algorithm based on multi-scale block and sparse representation is proposed. ...
In this paper, we propose a novel algorithm to deal with the problem of visual tracking in some challenging situations, which is based on sparse representation and multi-scale block. ...
Conclusion This paper presents a robust tracking algorithm via sparse representation and multi-scale block. ...
doi:10.14257/ijsip.2015.8.8.34
fatcat:o3ffdwuwzjf37g2n2ez3x247iu
Transferring Visual Prior for Online Object Tracking
2012
IEEE Transactions on Image Processing
During the tracking process, the learned visual prior is transferred to construct an object representation by sparse coding and multiscale max pooling. ...
Motivated by this, we propose an algorithm that transfers visual prior learned offline for online object tracking. ...
For visual tracking, we transfer the learned visual prior for object representation by sparse coding. ...
doi:10.1109/tip.2012.2190085
pmid:22491081
fatcat:obwthxkxqvag5eo6rwtqsaqpp4
« Previous
Showing results 1 — 15 out of 30,022 results