Context tracker: Exploring supporters and distracters in unconstrained environments

Dinh, Thang Ba; Vo, Nam D.; Medioni, Gérard

doi:10.1109/cvpr.2011.5995733

Cited by 454 publications

(282 citation statements)

References 32 publications

Supporting

Mentioning

279

Contrasting

Unclassified

Order By: Relevance

“…Most stateof-the-art methods rely on solely image intensity information [17,31,8,14,35,20,7], while others employ simple color space transformations [29,27,28]. On the contrary, feature representations have been thoroughly investigated in the related fields of object recognition and action recognition [22,21].…”

Section: Related Workmentioning

confidence: 99%

“…We compare our proposed feature representation with 15 state of the art trackers: CT [35], TLD [20], DFT [31], EDFT [8], ASLA [18], L1APG [2], CSK [17], SCM [36], LOT [28], CPF [29], CXT [7], Frag [1], Struck [14], LSHT [15] and LSST [32]. Table 2 shows the comparison of our tracker with the state-of-the-art tracking methods using median DP, OP and CLE.…”

Section: Experiments 2: State Of the Art Comparisonmentioning

confidence: 99%

“…Generic visual trackers can be categorized into generative [31,2,24,25] and discriminative [14,35,7,17,6] methods. The generative trackers search for image regions most similar to a generative appearance model.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Coloring Channel Representations for Visual Tracking

et al. 2015

View full text Add to dashboard Cite

Abstract. Visual object tracking is a classical, but still open research problem in computer vision, with many real world applications. The problem is challenging due to several factors, such as illumination variation, occlusions, camera motion and appearance changes. Such problems can be alleviated by constructing robust, discriminative and computationally efficient visual features. Recently, biologically-inspired channel representations [9] have shown to provide promising results in many applications ranging from autonomous driving to visual tracking. This paper investigates the problem of coloring channel representations for visual tracking. We evaluate two strategies, channel concatenation and channel product, to construct channel coded color representations. The proposed channel coded color representations are generic and can be used beyond tracking. Experiments are performed on 41 challenging benchmark videos. Our experiments clearly suggest that a careful selection of color feature together with an optimal fusion strategy, significantly outperforms the standard luminance based channel representation. Finally, we show promising results compared to state-of-the-art tracking methods in the literature.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Experiments 2: State Of the Art Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

Coloring Channel Representations for Visual Tracking

et al. 2015

View full text Add to dashboard Cite

show abstract

“…3. These trackers include Struck [8], SCM [45], TLD [15], ASLA [14], VTD [17], VTS [18], CXT [4], LSK [24], CSK [10], MTT [44] and LOT [27]. Note that all the plots are automatically generated by the code library supported by the benchmark providers.…”

Section: Experiments 1: Cvpr2013 Visual Tracker Benchmarkmentioning

confidence: 99%

Transfer Learning Based Visual Tracking with Gaussian Processes Regression

Gao

Ling

et al. 2014

Lecture Notes in Computer Science

355

288

View full text Add to dashboard Cite

Abstract. Modeling the target appearance is critical in many modern visual tracking algorithms. Many tracking-by-detection algorithms formulate the probability of target appearance as exponentially related to the confidence of a classifier output. By contrast, in this paper we directly analyze this probability using Gaussian Processes Regression (GPR), and introduce a latent variable to assist the tracking decision. Our observation model for regression is learnt in a semi-supervised fashion by using both labeled samples from previous frames and the unlabeled samples that are tracking candidates extracted from the current frame. We further divide the labeled samples into two categories: auxiliary samples collected from the very early frames and target samples from most recent frames. The auxiliary samples are dynamically re-weighted by the regression, and the final tracking result is determined by fusing decisions from two individual trackers, one derived from the auxiliary samples and the other from the target samples. All these ingredients together enable our tracker, denoted as TGPR, to alleviate the drifting issue from various aspects. The effectiveness of TGPR is clearly demonstrated by its excellent performances on three recently proposed public benchmarks, involving 161 sequences in total, in comparison with state-of-the-arts.

show abstract

“…We compare the proposed tracking methods (CLRST, LRST, LRT and ST) with 14 state-of-the-art visual trackers including visual tracking by decomposition (VTD) (Kwon and Lee 2010), 1 tracker , incremental visual tracking (IVT) method (Ross et al 2008), online multiple instance learning (MIL) (Babenko et al 2009) method, fragments-based (Frag) (Adam et al 2006) tracking method online Adabost boosting (OAB) method (Grabner et al 2006), multi-task tracking (MTT) (Zhang et al 2012d) method, circulant structure tracking (CST) method (Henriques et al 2012), real time compressive tracking (RTCT) method (Zhang et al 2012a), tracking by detection (TLD) method (Kalal et al 2010), context-sensitive tracking (CT) method (Dinh et al 2011), distribution field tracking (DFT) method (Sevilla-Lara and Learned-Miller 2012), sparse collaborative model (SCM) (Zhong et al 2012), and Struck (Hare et al 2011). For fair comparisons, we use the publicly available source or binary codes provided by the authors.…”

Section: Evaluated Algorithmsmentioning

confidence: 99%

Robust Visual Tracking Via Consistent Low-Rank Sparse Learning

et al. 2014

View full text Add to dashboard Cite

Object tracking is the process of determining the states of a target in consecutive video frames based on properties of motion and appearance consistency. In this paper, we propose a consistent low-rank sparse tracker (CLRST) that builds upon the particle filter framework for tracking. By exploiting temporal consistency, the proposed CLRST algorithm adaptively prunes and selects candidate particles. By using linear sparse combinations of dictionary templates, the proposed method learns the sparse representations of image regions corresponding to candidate particles jointly by exploiting the underlying low-rank constraints. In addition, the proposed CLRST algorithm is computationally attractive since temporal consistency property helps prune particles and the low-rank minimization problem for learning joint sparse representations can be efficiently solved by a sequence of closed form update operations. We evaluate the proposed CLRST algorithm against 14 state-of-the-art tracking methods on a set of 25 challenging image sequences. Experimental results show that the CLRST algorithm performs favorably against state-of-the-art tracking methods in terms of accuracy and execution time.

show abstract

Context tracker: Exploring supporters and distracters in unconstrained environments

Abstract: Abstract

Cited by 454 publications

References 32 publications

Coloring Channel Representations for Visual Tracking

Coloring Channel Representations for Visual Tracking

Transfer Learning Based Visual Tracking with Gaussian Processes Regression

Robust Visual Tracking Via Consistent Low-Rank Sparse Learning

Contact Info

Product

Resources

About