Sparse Hashing Tracking

Zhang, Lihe; Lu, Huchuan; Du, Dandan; Liu, Luning

doi:10.1109/tip.2015.2509244

Cited by 32 publications

(11 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…7: get the blur target template set T * by the blur kernel k which were used to convolved with target template set T. 8: calculate the reconstruction error of the candidate Y i with dictionary D 1 and D * 1 by the (8). 9: get the confidences of each candidates by (9). 10: extract the local descriptors from the sparse coding coefficients of the candidates Y, and use it to calculate the classification values of each candidate.…”

Section: Update Strategy Of Template Set and The Classifiermentioning

confidence: 99%

“…Visual tracking plays an important role in computer vision and image processing, since it has been widely applied to vision navigation, intelligent transportation and video surveillance. In recent years, more research have been obtained such as: [1], [2], [3], [4], [5], [6], [7], [8], [9], [10]. But the visual tracking still faces many challenges: 1) The videos sometimes introduce the motion blur which can change the structure information of the target area with pixel intensity and the gradient that makes it impossible to accurately identify the best candidates, and leads to the tracking drift or losing.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Visual Tracking Based on Cooperative Model

Zhang

Fang

Chen³

et al. 2018

2018 13th IEEE International Conference on Automatic Face &Amp; Gesture Recognition (FG 2018)

View full text Add to dashboard Cite

In this paper, we propose a cooperative model combined the multi-task reverse sparse representation model (MTRSR) and the AdaBoost classifier, which were used to cope with the disturbing of target gradient information caused by motion blur or target serious occlusion, and a descriptive dictionary were used to estimate the weights of each candidates. First, we use the MTRSR model to get the blur kernel which were used to get the blur target template set, meanwhile the confidence of the candidates is also obtained by the reconstruction error. Then we use the HOG features of the target templates to get the descriptive dictionary to calculate the weights of the candidates, and a AdaBoost classifier is used to calculate the confidences of all candidates. Finally, the best target is retrieved by the sum of production of weight value and the two confidences. The experimental data show that the proposed algorithm can fully cope with the target's information change which were caused by motion blur and target occlusion in the complex scene, and our algorithm can further improve the accuracy and robustness in visual tracking.

show abstract

Section: Update Strategy Of Template Set and The Classifiermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Visual Tracking Based on Cooperative Model

Zhang

Fang

Chen³

et al. 2018

2018 13th IEEE International Conference on Automatic Face &Amp; Gesture Recognition (FG 2018)

View full text Add to dashboard Cite

show abstract

“…The representation technique with sparse constraint is applied into visual tracking [15][16][17][18][19]. The target representations with sparsity are robust to outliers and occlusions.…”

Section: Introductionmentioning

confidence: 99%

Robust Visual Tracking with Discrimination Dictionary Learning

Wang

Deng

Wang

et al. 2018

Advances in Multimedia

View full text Add to dashboard Cite

It is a challenging issue to deal with kinds of appearance variations in visual tracking. Existing tracking algorithms build appearance models upon target templates. Those models are not robust to significant appearance variations due to factors such as illumination variations, partial occlusions, and scale variation. In this paper, we propose a robust tracking algorithm with a learnt dictionary to represent target candidates. With the learnt dictionary, a target candidate is represented with a linear combination of dictionary atoms. The discriminative information in learning samples is exploited. In the meantime, the learning processing of dictionaries can learn appearance variations. Based on the learnt dictionary, we can get a more stable representation for target candidates. Additionally, the observation likelihood is evaluated based on both the reconstruct error and dictionary coefficients with l1 constraint. Comprehensive experiments demonstrate the superiority of the proposed tracking algorithm to some state-of-the-art tracking algorithms.

show abstract

“…Hashing methods are efficient for approximate nearest neighbor (ANN) searching, which is important in computer vision [1][2] [3][4] and machine learning [5] [6][7] [8]. Hashing methods map original input data points to binary hash codes while preserving their mutual distances; that is, the binary strings of similar data points in the original feature space should have low Hamming distances.…”

Section: Introductionmentioning

confidence: 99%

Global Hashing System for Fast Image Search

Tian

Tao

2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-Hashing methods have been widely investigated for fast approximate nearest neighbor searching in large datasets. Most existing methods use binary vectors in lower dimensional spaces to represent data points, which are usually real vectors of higher dimensionality. However, according to Shannon's Source Coding Theorem (SSCT) in information theory, it is logical to represent low-dimensional real vectors with high-dimensional binary vectors, since a binary bit contains less information than a real number. We design a novel hashing method based on this principle. Data points are first embedded in a low-dimensional space, and then the Global Positioning System (GPS) method is introduced but modified for hashing. We devise data-independent and data-dependent methods to distribute the "satellites" at appropriate locations. Benefitting from the rationale of SSCT and rules on distributing satellites in a GPS, our data-dependent method outperforms other methods in different-sized datasets from 100K to 10M. By incorporating the orthogonality of the code matrix, both our data-independent and data-dependent methods are particularly impressive in experiments on longer bits.

show abstract

Sparse Hashing Tracking

Cited by 32 publications

References 30 publications

Visual Tracking Based on Cooperative Model

Visual Tracking Based on Cooperative Model

Robust Visual Tracking with Discrimination Dictionary Learning

Global Hashing System for Fast Image Search

Contact Info

Product

Resources

About