12,623 Hits in 2.9 sec

Patchwise object tracking via structural local sparse appearance model [article]

Hossein Kashiyani, Shahriar B. Shokouhi
2018 arXiv   pre-print
By applying this representation into structural sparse appearance model, we can take two-fold advantages. First, the correlation of target patches over time is considered.  ...  Second, using this local appearance model with different patch sizes takes into account local features of target thoroughly.  ...  of robust local appearance model using two patchwise dictionaries with different patch sizes.  Weighting patches in structural local sparse appearance model by utilizing patchwise reconstruction error  ... 
arXiv:1803.06141v1 fatcat:otmtesaiuve55olqiz6eppvppy

An approach to model human appearance based on sparse representation for human tracking in surveillance

Sangeetha D
2020 IET Image Processing  
Coarse and fine representation of sparse code facilitates tracking under varying scales.  ...  Sparse representation-based human appearance model utilises weighted gradient orientation that is insensitive to illumination variation.  ...  Local sparse appearance model via gradient orientation Structural local sparse appearance model or multiple holistic templates represent the target in many tracking algorithms.  ... 
doi:10.1049/iet-ipr.2018.5961 fatcat:xvgxthgwkrd4jloup4xevtaiqe

Robust Object Tracking via Reverse Low-Rank Sparse Learning and Fractional-Order Variation Regularization

Dan Tian, Guoshan Zhang, Shouyu Zang
2020 Mathematical Problems in Engineering  
Thirdly, we employ an inverse sparse representation method to model the relationship between target candidates and target template, which can reduce the computation complexity for online tracking.  ...  Object tracking based on low-rank sparse learning usually makes the drift phenomenon occur when the target faces severe occlusion and fast motion.  ...  [15] formulate spatial-temporal locality under a discriminative dictionary learning structure for object tracking.  ... 
doi:10.1155/2020/8640724 fatcat:6kkkuj2mqbgvzdq2uduljocrhm

Object tracking using a convolutional network and a structured output SVM

Junwei Li, Xiaolong Zhou, Sixian Chan, Shengyong Chen
2017 Computational Visual Media  
In this paper, we present a novel method to model target appearance and combine it with structured output learning for robust online tracking within a tracking-by-detection framework.  ...  Object tracking has been a challenge in computer vision.  ...  The sparse feature vector c in Eq. (5) is used as the object feature template. It is updated incrementally to accommodate appearance changes over time for robust visual tracking.  ... 
doi:10.1007/s41095-017-0087-3 fatcat:4miqlot67vhpfc2idgyag4ka5a

Visual tracking via adaptive structural local sparse appearance model

Xu Jia, Huchuan Lu, Ming-Hsuan Yang
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper we develop a simple yet robust tracking method based on the structural local sparse appearance model.  ...  Sparse representation has been applied to visual tracking by finding the best candidate with minimal reconstruction error using target templates.  ...  Furthermore, our tracker is not affected much by occlusion owing to the structural local sparse appearance model and robust template update scheme.  ... 
doi:10.1109/cvpr.2012.6247880 dblp:conf/cvpr/JiaLY12 fatcat:4vzbrlsygnhives5kuervlwvte

A Tracking Method with Structural Local Mean and Local Standard Deviation Appearance Model [chapter]

Dawei Yang, Yang Cong, Yandong Tang, Yulian Li
2014 Communications in Computer and Information Science  
Aiming at the problem of illumination variation and partial occlusion in the object tracking, a structural local mean and local standard deviation appearance model is proposed.  ...  The Native Bayesian theory is applied to track the object in affine transform space.  ...  [14] proposed a tracking algorithm based on local sparse model which employs histograms of sparse coefficients and the mean-shift algorithm for object tracking.  ... 
doi:10.1007/978-3-662-45646-0_36 fatcat:i7yntv5debfafpfkidbapgwmzm

Online Learning Discriminative Dictionary with Label Information for Robust Object Tracking

Baojie Fan, Yingkui Du, Yang Cong
2014 Abstract and Applied Analysis  
A supervised approach to online-learn a structured sparse and discriminative representation for object tracking is presented.  ...  As the tracking continues, the proposed algorithm alternates between robust sparse coding and dictionary updating.  ...  The project was supported by the Jiangsu Key Laboratory of Image and Video Understanding for Social Safety (Nanjing University of Science and Technology), Grant no. 30920140122007.  ... 
doi:10.1155/2014/189317 fatcat:ri26ch4h5jbctn55lymnyyhl6a

Robust Outdoor Vehicle Visual Tracking Based on k-Sparse Stacked Denoising Auto-Encoder [chapter]

Jing Xin, Xing Du, Yaqian Shi, Jian Zhang, Ding Liu
2018 Autonomous Vehicles [Working Title]  
Robust visual tracking for outdoor vehicle is still a challenging problem due to large object appearance variations caused by illumination variation, occlusion, and fast motion.  ...  In this chapter, k-sparse constraint is added to the encoder part of stacked auto-encoder network to learn more invariant feature of object appearance, and a stacked k-sparse-autoencoder-based robust outdoor  ...  of the tracking method based on the appearance model.  ... 
doi:10.5772/intechopen.80089 fatcat:oskoxmu3qnbtldeavke2hu3joa

Optimal Metric Evaluation-Based Multicue Inverse Sparse Appearance Model for Object Tracking

Xiaowei An, Qi Zhao, Nongliang Sun, Quanquan Liang, Stylianos Georgantzinos
2020 Mathematical Problems in Engineering  
In order to obtain the discriminative compact appearance model for tracking objects effectively, this paper proposes a new structural tracking strategy that includes multicue inverse sparse appearance  ...  It also alleviates the accuracy degradation of tracking occluded objects and improves the robustness of the tracker.  ...  Although the OBIS and OPF trackers have much simpler structures and faster tracking speed than the proposed method, they do not own efficient and robust appearance models for test video sequences.  ... 
doi:10.1155/2020/1248064 fatcat:ubpmpkx64fchxmgddkhvah3dtu

Correlation Tracking via Spatial-Temporal Constraints and Structured Sparse Regularization

Dan Tian, Shouyu Zang, Binbin Tu
2021 IEEE Access  
Drastic appearance changes of the target object are the main challenge for robust tracking.  ...  The last term restricts the filters with structured sparse regularization. The standard 1 L sparse regularization of the filters can manage the major local appearance changes of the target object.  ... 
doi:10.1109/access.2021.3086821 fatcat:nrjp7qxlirazzltbjouq7tqdaq

Mask Sparse Representation Based on Semantic Features for Thermal Infrared Target Tracking

Meihui Li, Lingbing Peng, Yingpin Chen, Suqi Huang, Feiyi Qin, Zhenming Peng
2019 Remote Sensing  
The sparse representation, as a typical appearance modeling approach, has been successfully exploited in the TIR target tracking.  ...  To address this issue, we propose a mask sparse representation (MaskSR) model, which combines sparse coding together with high-level semantic features for TIR target tracking.  ...  method for target appearance modeling.  ... 
doi:10.3390/rs11171967 fatcat:ete3t4odhjbutet4dfja5cuqse

Robust Object Tracking via Sparse Collaborative Appearance Model

Wei Zhong, Huchuan Lu, Ming-Hsuan Yang
2014 IEEE Transactions on Image Processing  
In this paper, we propose a robust object tracking algorithm based on a sparse collaborative model that exploits both holistic templates and local representations to account for drastic appearance changes  ...  Within the proposed collaborative appearance model, we develop a sparse discriminative classifier (SDC) and sparse generative model (SGM) for object tracking.  ...  Within the proposed collaborative appearance model, we develop a sparse discriminative classifier (SDC) and sparse generative model (SGM) for object tracking.  ... 
doi:10.1109/tip.2014.2313227 pmid:24686280 fatcat:l64n2ystxjhk5jt2bef63btmki

Robust Visual Tracking via Exclusive Context Modeling

Tianzhu Zhang, Bernard Ghanem, Si Liu, Changsheng Xu, Narendra Ahuja
2016 IEEE Transactions on Cybernetics  
In this paper, we formulate particle filter-based object tracking as an exclusive sparse learning problem that exploits contextual information.  ...  To achieve this goal, we propose the context-aware exclusive sparse tracker (CEST) to model particle appearances as linear combinations of dictionary templates that are updated dynamically.  ...  In that spirit, we go beyond representing the target appearance and exploit context information for more robust object tracking.  ... 
doi:10.1109/tcyb.2015.2393307 pmid:25680224 fatcat:d2qvsk2xfzactdu4mhwffcuhpu

Dual Deep Network for Visual Tracking

Zhizhen Chi, Hongyang Li, Huchuan Lu, Ming-Hsuan Yang
2017 IEEE Transactions on Image Processing  
In this paper, we propose a dual network to better utilize features among layers for visual tracking.  ...  the dual network to focus on target object.  ...  Let g D (·) denote the object appearance model by thresholding the object of interest out of g D (·).  ... 
doi:10.1109/tip.2017.2669880 pmid:28212087 fatcat:3d6dcnroobb6peuku776fosmte

Handcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends [article]

Mustansar Fiaz, Arif Mahmood, Sajid Javed, Soon Ki Jung
2019 arXiv   pre-print
In the second part, we experimentally evaluated 24 recent trackers for robustness, and compared handcrafted and deep feature based trackers.  ...  In recent years visual object tracking has become a very active research area. An increasing number of tracking algorithms are being proposed each year.  ...  (a) global sparse representation [99], (b) local sparse representation model [76], (c) joint sparse representation model [190] and (d) structural sparse representation model [194].  ... 
arXiv:1812.07368v2 fatcat:e342qc453vemnfr63xdksyucfe
« Previous Showing results 1 — 15 out of 12,623 results