Robust Fragments-based Tracking using the Integral Histogram

Adam, A.; Rivlin, Ehud; Shimshoni, Ilan

doi:10.1109/cvpr.2006.256

Cited by 1,109 publications

(1,088 citation statements)

References 23 publications

Supporting

Mentioning

1,074

Contrasting

Unclassified

Order By: Relevance

“…These sequences cover the most challenge situations in object tracking: heavy occlusion, motion blur, in-plane and out-of-plane rotation, large illumination change, scale variation and complex background. We will compare our tracking experiment result with five algorithms: Frag tracker [11], L1 tracker [5], MIL tracer [8], and ODLSR tracker [16]. The tracking results of the compared methods were obtained by running the source code or binaries provided by their authors using the same initial positions in the first frame.…”

Section: Resultsmentioning

confidence: 99%

“…It's robust in handling occlusion, scaling and rotation. Adam et al [11] presents the "frag-track" algorithm to handle the occlusions problem. The object is represented by randomly multiple image fragments or patches.…”

Section: Related Workmentioning

confidence: 99%

“…In fact, occlusion is one of the most general problems in object tracking. Frag tracker [11], L1 tracker [5], ODLSR tracker and the propose method are develop to solve the problem. Fig.…”

Section: B Qualitative Comparison Occlusionmentioning

confidence: 99%

“…Discriminative methods formulate the tracking as a binary classification problem [8]- [11] to find a best decision boundary that can best separate the target from background. For using the background information, these method can be strong robustness to avoid the target judgment as background.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Robust Object Tracking via Multi-block and Sparsity-Based Representation

Wu¹,

Tao²,

Ye³

et al. 2015

IJKE

View full text Add to dashboard Cite

Abstract-In this paper, we propose a robust object tracking algorithm based on classifier, multi-block and local sparse coding with multiple discriminative dictionary. The first part of the propose method is train a classifier with the dictionary encodes the information of both target information and background information. The second part exploits the block information of the object target. The different blocks in a sample should contribute differently to the visual tracking, the model effectively exploit the similarity and distinctiveness of different blocks. Each block is coded on its own discriminative dictionary to allow flexible coding block and the parameter after sparse coding can be used for the weights allocation simultaneously. Furthermore, the update scheme considers both the latest observations and the original template, thereby enabling to alleviate drift problem. Extensive experiments on challenging sequences show that the robust tracking achieved by our algorithm.Index Terms-Visual tracking, sparse representation, multi-block.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…In fact, occlusion is one of the most general problems in object tracking. Frag tracker [11], L1 tracker [5], ODLSR tracker and the propose method are develop to solve the problem. Fig.…”

Section: B Qualitative Comparison Occlusionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Robust Object Tracking via Multi-block and Sparsity-Based Representation

Wu¹,

Tao²,

Ye³

et al. 2015

IJKE

View full text Add to dashboard Cite

show abstract

“…In these methods, visual tracking is formulated as an online binary classification problem and the target appearance is updated adaptively using the images tracked from the previous frames. Compared with the approaches using fixed target models, such as [5], these adaptive approaches are more robust to appearance changes. However, the main drawback of these appearance-adaptive approaches is their sensitivity to drift, i.e., they may gradually adapt to non-targets.…”

Section: Introductionmentioning

confidence: 99%

Visual tracking via weakly supervised learning from multiple imperfect oracles

Zhong

Yao

Chen

et al. 2014

Pattern Recognition

View full text Add to dashboard Cite

show abstract

A robust tracking method with adaptive local spatial sparse representation

Zhang

Zhu

et al. 2015

Math Methods in App Sciences

View full text Add to dashboard Cite

Communicated by T. QianIn this paper, a robust visual tracking method is proposed based on local spatial sparse representation. In the proposed approach, the learned target template is sparsely and compactly expressed by forming local spatial and trivial samples dynamically. An adaptive multiple subspaces appearance model is developed to describe the target appearance and construct the candidate target templates during the tracking process. An effective selection strategy is then employed to select the optimal sparse solution and locate the target accurately in the next frame. The experimental results have demonstrated that our method can perform well in the complex and noisy visual environment, such as heavy occlusions, dramatic illumination changes, and large pose variations in the video.

show abstract

Robust Fragments-based Tracking using the Integral Histogram

Abstract: We present a novel algorithm (which we call "FragTrack")

Cited by 1,109 publications

References 23 publications

Robust Object Tracking via Multi-block and Sparsity-Based Representation

Robust Object Tracking via Multi-block and Sparsity-Based Representation

Visual tracking via weakly supervised learning from multiple imperfect oracles

A robust tracking method with adaptive local spatial sparse representation

Contact Info

Product

Resources

About